Journals starting with eccv

ECCV00 * *ECCV
* 3-D Motion and Structure from 2-D Motion Causally Integrated over Time: Implementation
* 3D Reconstruction from Tangent-of-Sight Measurements of a Moving Object Seen from a Moving Camera
* Adapting Spectral Scale for Shape from Texture
* Ambiguous Configurations for 3-View Projective Reconstruction
* Anti-Faces for Detection
* Approximate N-View Stereo
* Approximation and Processing of Intensity Images with Discontinuity-Preserving Adaptive Triangular Meshes
* Binocular Self-Alignment and Calibration from Planar Scenes
* Bootstrap Initialization of Nonparametric Texture Models for Tracking
* Calibrating Parameters of Cost Functionals
* Calibration of a Moving Camera Using a Planar Pattern: Optimal Computation, Reliability Evaluation, and Stabilization by Model Selection
* Camera Pose Estimation and Reconstruction from Image Profiles under Circular Motion
* Can We Calibrate a Camera Using an Image of a Flat, Textureless Lambertian Surface?
* Characterizing Depth Distortion due to Calibration Uncertainty
* Color and Scale: The Spatial Structure of Color Images
* Colour by Correlation in a Three-Dimensional Colour Space
* Colour Image Retrieval and Object Recognition Using the Multimodal Neighbourhood Signature
* Combining Elastic and Statistical Models of Appearance Variation
* Computation of the Mid-Sagittal Plane in 3D Images of the Brain
* Constrained Dichromatic Colour Constancy
* Construction of 3 Dimensional Models Using an Active Computer Vision System, The
* Contour-based Correspondence for Stereo
* Coupled Geodesic Active Regions for Image Segmentation: A Level Set Approach
* Data-Driven Extraction of Curved Intersection Lanemarks from Road Traffic Image Sequences
* Determining Correspondences for Statistical Models of Appearance
* Diffeomorphic Matching Problems in One Dimension: Designing and Minimizing Matching Functionals
* Direction Control for an Active Docking Behaviour based on the Rotational Component of Log-Polar Optic Flow
* Divergence-Based Medial Surfaces
* Duals, Invariants, and the Recognition of Smooth Objects from their Occluding Contour
* Egomotion Estimation Using Quadruples of Collinear Image Points
* Estimating the Jacobian of the Singular Value Decomposition: Theory and Applications
* Euclidean Group Invariant Computation of Stochastic Completion Fields Using Shiftable-Twistable Functions
* Factorization with Uncertainty
* Fast Selective Detection of Rotational Symmetries Using Normalized Inhibition
* General Method for Unsupervised Segmentation of Images Using a Multiscale Approach, A
* Geometric Driven Optical Flow Estimation and Segmentation for 3D Reconstruction
* Geotensity Constraint for 3D Surface Reconstruction under Multiple Light Sources
* Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns
* Hand-Eye Calibration from Image Derivatives
* Homography Tensors: On Algebraic Entities That Represent Three Views of Static or Moving Planar Points
* How Does CONDENSATION Behave with a Finite Number of Samples?
* Image Segmentation by Nonparametric Clustering based on the Kolmogorov-Smirnov Distance
* Improvements to Gamut Mapping Colour Constancy Algorithms
* IMPSAC: Synthesis of Importance Sampling and Random Sample Consensus
* Integrating Local Affine into Global Projective Images in the Joint Image Space
* Intrinsic Images for Dense Stereo Matching with Occlusions
* Kruppa Equation Revisited: its Renormalization and Degeneracy
* Layer Extraction with a Bayesian Model of Shapes
* Learning Over Multiple Temporal Scales in Image Databases
* Learning Similarity for Texture Image Retrieval
* Learning to Recognize 3D Objects with SNoW
* Least Commitment Graph Matching by Evolutionary Optimisation
* Level Lines as Global Minimizers of Energy Functionals in Image Segmentation
* Level Sets and Distance Functions
* Local Scale Selection for Gaussian Based Description Techniques
* Log-Polar Stereo for Anthropomorphic Robots
* Measuring the Self-Consistency of Stereo Algorithms
* Minimal Paths in 3D Images and Application to Virtual Endoscopy
* Minimal Set of Constraints for the Trifocal Tensor, A
* Model Based Pose Estimator Using Linear-Programming
* Model-Based Initialisation for Segmentation
* Monocular Perception of Biological Motion: Clutter and Partial Occlusion
* Motion Segmentation by Tracking Edge Information over Multiple Frames
* Multi-View Constraints between Collineations: Application to Self-Calibration from Unknown Planar Structures
* Multibody Structure and Motion: 3-D Reconstruction of Independently Moving Objects
* Multimodal Elastic Matching of Brain Images
* Nautical Scene Segmentation using Variable Size Image Windows and Feature Space Reclustering
* New Algorithms for Controlling Active Contours Shape and Topology
* Noise-Resistant Affine Skeletons of Planar Curves
* Non-Linear Bayesian Image Modelling
* Non-Parametric Model for Background Subtraction
* Object Recognition using Coloured Receptive Fields
* Objective Colour from Multispectral Imaging
* On Calibration and Reconstruction from Planar Curves
* On the Estimation of the Fundamental Matrix: A Convex Approach to Constrained Least-Squares
* On the Performance Characterisation of Image Segmentation Algorithms: A Case Study
* On the Reprojection of 3D and 2D Scenes Without Explicit Model Selection
* On the Structure and Properties of the Quadrifocal Tensor
* On Utilising Template and Feature-based Correspondence in Multi-view Appearance Models
* On Weighting and Choosing Constraints for Optimally Reconstructing the Geometry of Image Triplets
* Parametric View-Synthesis
* Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking
* Pedestrian Detection from a Moving Vehicle
* Physically-Based Statistical Deformable Model for Brain Image Analysis, A
* Plane + Parallax, Tensors, and Factorization
* Predicting Disparity Windows for Real-Time Stereo
* Probabilistic Background Model for Tracking, A
* Probabilistic Interpretation of the Saliency Network, A
* Probabilistic Sensor for the Perception and the Recognition of Activities, A
* Qualitative Spatiotemporal Analysis Using an Oriented Energy Representation
* Quasi-Random Sampling for Condensation
* Real-time Tracking of Multiple Articulated Structures in Multiple Views
* Recognizing Walking People
* Reconstruction from Uncalibrated Sequences with a Hierarchy of Trifocal Tensors
* Region-based Object Recognition using Shape-from-Shading
* Registration with a Moving Zoom Lens Camera for Augmented Reality Applications
* Regularised Range Flow
* Role of Self-Calibration in Euclidean Reconstruction from Two Rotating and Zooming Cameras, The
* Scale Dependent Differential Geometry for the Measurement of Center Line and Diameter in 3D Curvilinear Structures
* Shape and Radiance Estimation from the Information Divergence of Blurred Images
* Significantly Different Textures: A Computational Model of Pre-Attentive Texture Segmentation
* Six Point Solution for Structure and Motion, A
* Statistical Foreground Modelling for Object Localisation
* Statistical Significance as an Aid to System Performance Evaluation
* Stereo Autocalibration From One Plane
* Stochastic Tracking of 3D Human Figures using 2D Image Motion
* Surface Matching with Large Deformations and Arbitrary Topology: A Geodesic Distance Evolution Scheme on a 3-Manifold
* Tracking and Characterization of Highly Deformable Cloud Structures
* Tracking Discontinuous Motion using Bayesian Inference
* Underwater Camera Calibration
* Unifying Theory for Central Panoramic Systems and Practical Implications, A
* Unsupervised Learning of Models for Recognition
* Velocity-Guided Tracking of Deformable Contours in Three Dimensional Space
* Vision-based Guidance and Control of Robots in Projective Space
* Visual Encoding of Tilt from Optic Flow: Psychophysics and Computational Modelling
* Wide Baseline Point Matching using Affine Invariants Computed from Intensity Profiles
117 for ECCV00

ECCV02 * *ECCV
* 3D Modelling Using Geometric Constraints: A Parallelepiped Based Approach
* 3D Statistical Shape Models Using Direct Optimisation of Description Length
* Accurate and Efficient Bayesian Method for Automatic Segmentation of Brain MRI, An
* Active Surface Reconstruction Using the Gradient Strategy
* Adaptive Rest Condition Potentials: Second Order Edge-Preserving Regularization
* Adjustment Learning and Relevant Component Analysis
* Affine Invariant Interest Point Detector, An
* All the Images of an Outdoor Scene
* Analytical Image Models and Their Applications
* Another Way of Looking at Plane-Based Calibration: The Centre Circle Constraint
* Approximate Thin Plate Spline Mappings
* Assorted Pixels: Multi-sampled Imaging with Structural Models
* Audio-Video Sensor Fusion with Probabilistic Graphical Models
* Automatic Camera Calibration from a Single Manhattan Image
* Automatic Detection and Tracking of Human Motion with a View-Based Representation
* Automatic Model Selection by Modelling the Distribution of Residuals
* Balanced Recovery of 3D Structure and Camera Motion from Uncalibrated Image Sequences
* Bayesian Estimation of Building Shape Using MCMC, A
* Bayesian Estimation of Layers from Multiple Images
* Bayesian Self-Calibration of a Moving Camera
* Bidirectional Texture Contrast Function
* Building Architectural Models from Many Views Using Map Constraints
* Building Roadmaps of Local Minima of Visual Models
* Camera Calibration with One-Dimensional Objects
* Class-Specific, Top-Down Segmentation
* Classification and Localisation of Diabetic-Related Eye Disease
* Classifying Images of Materials: Achieving Viewpoint and Illumination Independence
* Coarse Registration of Surface Patches with Local Symmetries
* Color-Based Probabilistic Tracking
* Combining Appearance and Topology for Wide Baseline Matching
* Combining Simple Discriminators for Object Discrimination
* Comparing Intensity Transformations and Their Invariants in the Context of Color Pattern Recognition
* Comparison of Search Strategies for Geometric Branch and Bound Algorithms, A
* Composite Texture Descriptions
* Computing Content-Plots for Video
* Computing the Physical Parameters of Rigid-Body Motion from Video
* Constrained Flows of Matrix-Valued Functions: Application to Diffusion Tensor Regularization
* Constructing Illumination Image Basis from Object Motion
* Critical Curves and Surfaces for Euclidean Reconstruction
* Deformable Model with Non-euclidean Metrics
* DEFORMOTION: Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images
* Dense Motion Analysis in Fluid Imagery
* Dense Structure-from-Motion: An Approach Based on Segment Matching
* Diffuse-Specular Separation and Depth Recovery from Image Sequences
* Dramatic Improvements to Feature Based Stereo
* DREAM 2 S: Deformable Regions Driven by an Eulerian Accurate Minimization Method for Image and Video Segmentation
* Dynamic Trees: Learning to Model Outdoor Scenes
* Dynamism of a Dog on a Leash or Behavior Classification by Eigen-Decomposition of Periodic Motions
* Effect of Illuminant Rotation on Texture Filters: Lissajous's Ellipses, The
* EigenSegments: A Spatio-Temporal Decomposition of an Ensemble of Images
* Estimating Human Body Configurations Using Shape Context Matching
* Estimation of Illuminant Direction and Intensity of Multiple Light Sources
* Estimation of Multiple Illuminants from a Single Image of Arbitrary Known Geometry
* Evaluating Image Segmentation Algorithms Using the Pareto Front
* Evaluation and Selection of Models for Motion Segmentation
* Exemplar-Based Face Recognition from Video
* Eye Gaze Correction with Stereovision for Video-Teleconferencing
* Face Identification by Fitting a 3D Morphable Model Using Linear Shape and Texture Error Functions
* Face Recognition from Long-Term Observations
* Factorial Markov Random Fields
* Fast Anisotropic Gauss Filtering
* Fast Difference Schemes for Edge Enhancing Beltrami Flow
* Fast Radial Symmetry Transform for Detecting Points of Interest, A
* Feature-Preserving Medial Axis Noise Removal
* Finding Deformable Shapes Using Loopy Belief Propagation
* Finding the Largest Unambiguous Component of Stereo Matching
* Framework for High-Level Feedback to Adaptive, Per-Pixel, Mixture-of-Gaussian Background Models, A
* Fusion of Multiple Tracking Algorithms for Robust People Tracking
* Gait Sequence Analysis Using Frieze Patterns
* General Trajectory Triangulation
* Generalized Rank Conditions in Multiple View Geometry with Applications to Dynamical Scenes
* Generative Method for Textured Motion: Analysis and Synthesis, A
* Geometric Properties of Central Catadioptric Line Images
* Guided Sampling and Consensus for Motion Estimation
* Hausdorff Kernel for 3D Object Acquisition and Detection
* Helmholtz Stereopsis: Exploiting Reciprocity for Surface Reconstruction
* Hierarchical Framework for Spectral Correspondence, A
* Hierarchical Shape Modeling for Automatic Face Localization
* Highlight Removal Using Shape-from-Shading
* Hyperdynamics Importance Sampling
* Image Features Based on a New Approach to 2D Rotation Invariant Quadrature Filters
* Image Processing Done Right
* Image Registration for Foveated Omnidirectional Sensing
* Image Segmentation by Flexible Models Based on Robust Regularized Networks
* Implicit Probabilistic Models of Human Motion for Synthesis and Tracking
* Increasing Space-Time Resolution in Video
* Incremental Singular Value Decomposition of Uncertain Data with Missing Values
* Interpolating Sporadic Data
* Is Super-Resolution with Optical Flow Feasible?
* Layered Motion Representation with Occlusion and Compact Spatial Support, A
* Learning a Sparse Representation for Object Detection
* Learning Intrinsic Video Content Using Levenshtein Distance in Graph Partitioning
* Learning Montages of Transformed Latent Images as Representations of Objects That Change in Appearance
* Learning Shape from Defocus
* Learning the Topology of Object Views
* Learning to Parse Pictures of People
* Lens Distortion Recovery for Accurate Sequential Structure and Motion Recovery
* Linear Multi View Reconstruction with Missing Data
* Linear Pose Estimation from Points or Lines
* Local Analysis for 3D Reconstruction of Specular Surfaces: Part II
* Localized Consistency Principle for Image Matching under Non-uniform Illumination Variation and Affine Distortion, The
* M2Tracker: A Multi-view Approach to Segmenting and Tracking People in a Cluttered Scene Using Region-Based Stereo
* Markov Chain Monte Carlo Approach to Stereovision, A
* Matching and Embedding through Edit-Union of Trees
* Matching Distance Functions: A Shape-to-Area Variational Approach for Global-to-Local Registration
* Maximizing Rigidity: Optimal Matching under Scaled-Orthography
* Minimal Surfaces for Stereo
* Model Acquisition by Registration of Multiple Acoustic Range Views
* Model-Based Silhouette Extraction for Accurate People Tracking
* Motion Curves for Parametric Shape and Motion Estimation
* Motion-Stereo Integration for Depth Estimation
* Multi-camera Scene Reconstruction via Graph Cuts
* Multi-scale EM-ICP: A Fast and Robust Approach for Surface Registration
* Multi-view Matching for Unordered Image Sets, or How Do I Organize My Holiday Snaps?
* Multilinear Analysis of Image Ensembles: TensorFaces
* Multimodal Data Representations with Parameterized Local Structures
* Multiple Hypothesis Tracking for Automatic Optical Motion Capture
* Multivariate Saddle Point Detection for Statistical Clustering
* Multiview Registration of 3D Scenes by Minimizing Error between Coordinate Frames
* Neuro-Fuzzy Shadow Filter
* New Image Registration Technique with Free Boundary Constraints: Application to Mammography, A
* New Techniques for Automated Architectural Reconstruction from Photographs
* New View Generation with a Bi-centric Camera
* Nonlinear Shape Statistics in Mumford-Shah Based Segmentation
* Normalized Gradient Vector Diffusion and Image Segmentation
* Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary
* On Affine Invariant Clustering and Automatic Cast Listing in Movies
* On Pencils of Tangent Planes and the Recognition of Smooth 3D Shapes from Silhouettes
* On Performance Characterization and Optimization for Image Retrieval
* On the Motion and Appearance of Specularities in Image Sequences
* On the Non-linear Optimization of Projective Motion Using Minimal Parameters
* On the Representation and Matching of Qualitative Shape at Multiple Scales
* Optimization Algorithms for the Selection of Key Frame Sequences of Variable Length
* Pairwise Clustering with Matrix Factorisation and the EM Algorithm
* Parameter Estimates for a Pencil of Lines: Bounds and Estimators
* Parametric Distributional Clustering for Image Segmentation
* Parsing Images into Region and Curve Processes
* PDE Approach for Thickness, Correspondence, and Gridding of Annular Tissues, A
* Perceptual Grouping from Motion Cues Using Tensor Voting in 4-D
* Phase-Based Local Features
* Principal Component Analysis over Continuous Subspaces and Intersection of Half-Spaces
* Probabalistic Models and Informative Subspaces for Audiovisual Correspondence
* Probabilistic and Voting Approaches to Cue Integration for Figure-Ground Segmentation
* Probabilistic Framework for Spatio-Temporal Video Representation & Indexing, A
* Probabilistic Human Recognition from Video
* Probabilistic Multi-scale Model for Contour Completion Based on Image Statistics, A
* Probabilistic Search for Object Segmentation and Recognition
* Probabilistic Theory of Occupancy and Emptiness, A
* Properties of the Catadioptric Fundamental Matrix
* Pseudo-Metric for Weighted Point Sets, A
* Quasi-Dense Reconstruction from Image Sequence
* Real-Time Interactive Path Extraction with on-the-Fly Adaptation of the External Forces
* Recognizing and Tracking Human Action
* Recovering Surfaces from the Restoring Force
* Recovery of Reflectances and Varying Illuminants from Multiple Views
* Rectilinearity Measurement for Polygons, A
* Reflective Symmetry Descriptor, A
* Region Matching with Missing Parts
* Registration Assisted Image Smoothing and Segmentation
* Regularized Shock Filters and Complex Diffusion
* Relevance of Non-Generic Events in Scale Space Models, The
* Removing Shadows from Images
* Representing Edge Models via Local Principal Component Analysis
* Resolution Selection Using Generalized Entropies of Multiresolution Histograms
* Revisiting Single-View Shape Tensors: Theory and Applications
* Robust Active Shape Model Search
* Robust Computer Vision through Kernel Density Estimation
* Robust Parameterized Component Analysis
* Robust PCA Algorithm for Building Representations from Panoramic Images, A
* Self-Organization of Randomly Placed Sensors
* Sensitivity of Calibration to Principal Point Position
* Sequence-to-Sequence Self Calibration
* Shadow Graphs and Surface Reconstruction
* Shape from Shading and Viscosity Solutions
* Shape from Texture without Boundaries
* Shape Priors for Level Set Representations
* Shock-Based Indexing into Large Shape Databases
* Single Axis Geometry by Fitting Conics
* SoftPOSIT: Simultaneous Pose and Correspondence Determination
* Space-Time Tracking
* Spectral Partitioning with Indefinite Kernels Using the Nyström Extension
* Specularities Reduce Ambiguity of Uncalibrated Photometric Stereo
* Statistical Characterization of Morphological Operator Sequences
* Statistical Learning of Multi-view Face Detection
* Statistical Modeling of Texture Sketch
* Stereo Matching Using Belief Propagation
* Stereo Matching with Segmentation-Based Cooperation
* Stochastic Algorithm for 3D Scene Segmentation and Reconstruction, A
* Stratified Self Calibration from Screw-Transform Manifolds
* Structure and Motion for Dynamic Scenes: The Case of Points Moving in Planes
* Structure from Many Perspective Images with Occlusions
* Structure from Planar Motions with Small Baselines
* Surface Extraction from Volumetric Images Using Deformable Meshes: A Comparative Study
* Surviving Dominant Planes in Uncalibrated Structure and Motion Recovery
* Symmetric Sub-Pixel Stereo Matching
* Symmetrical Dense Optical Flow Estimation with Occlusions Detection
* Tale of Two Classifiers: SNoW vs. SVM in Visual Recognition, A
* Texture Similarity Measure Using Kullback-Leibler Divergence between Gamma Distributions
* Time-Recursive Velocity-Adapted Spatio-Temporal Scale-Space Filters
* Toward a Full Probability Model of Edges in Natural Images
* Towards Improved Observation Models for Visual Tracking: Selective Adaptation
* Towards Real-Time Cue Integration by Using Partial Results
* Tracking and Object Classification for Automated Surveillance
* Tracking and Rendering Using Dynamic Textures on Geometric Structure from Motion
* Tracking with the EM Contour Algorithm
* Transitions of the 3D Medial Axis under a One-Parameter Family of Deformations
* Understanding and Modeling the Evolution of Critical Points under Gaussian Blurring
* Unified Approach to Model-Based and Model-Free Visual Servoing, An
* Using Dirichlet Free Form Deformation to Fit Deformable Models to Noisy 3-D Data
* Using Robust Estimation Algorithms for Tracking Explicit Curves
* Variational Approach to Recovering a Manifold from Sample Points, A
* Variational Approach to Shape from Defocus, A
* Very Fast Template Matching
* Video Compass
* Video Summaries through Mosaic-Based Shot and Scene Clustering
* Video-Based Drowning Detection System, A
* View Synthesis with Occlusion Reasoning Using Quasi-Sparse Feature Correspondences
* Visual Data Fusion for Objects Localization by Active Vision
* Volterra Filtering of Noisy Images of Curves
* Wavelet-Based Correlation for Stereopsis
* What are Textons?
* What Can Be Known about the Radiometric Response from Images?
* What Does the Scene Look Like from a Scene Point?
* What Energy Functions Can Be Minimized via Graph Cuts?
* What Is the Role of Independence for Visual Recognition?
* Yet Another Survey on Image Segmentation: Region and Boundary Information Integration
227 for ECCV02

ECCV04 * *ECCV
* A/1-Unified Variational Framework for Image Restoration
* Accuracy Certified Augmented Reality System for Therapy Guidance, An
* Accuracy of Spherical Harmonic Approximations for Images of Lambertian Objects under Far and Near Lighting
* Adaptive Probabilistic Visual Tracking with Incremental Subspace Update
* Adaptive Window Approach for Image Smoothing and Structures Preserving, An
* Affine Invariant Salient Region Detector, An
* Appearance Based Qualitative Image Description for Object Class Recognition
* Are Iterations and Curvature Useful for Tensor Voting?
* Audio-Video Integration for Background Modelling
* Automated Optic Disc Localization and Contour Detection Using Ellipse Fitting and Wavelet Transform
* Automatic Non-rigid 3D Modeling from Video
* Bayesian Correction of Image Intensity with Spatial Consideration
* Bayesian Framework for Multi-cue 3D Object Tracking, A
* Bias in Shape Estimation
* Bias in the Localization of Curved Edges
* Biologically Motivated and Computationally Tractable Model of Low and Mid-Level Vision Tasks, A
* Boosted Particle Filter: Multitarget Detection and Tracking, A
* Camera Calibration from the Quasi-affine Invariance of Two Parallel Circles
* Camera Calibration with Two Arbitrary Coplanar Circles
* Can We Consider Central Catadioptric Cameras and Fisheye Cameras within a Unified Imaging Model
* Causal Camera Motion Estimation by Condensation and Robust Statistics Distance Measures
* Characterization of Human Faces under Illumination Variations Using Rank, Integrability, and Symmetry Constraints
* Classifying Materials from Their Reflectance Properties
* Co-operative Multi-target Tracking and Classification
* Coaxial Omnidirectional Stereopsis
* Color Constancy Using Local Color Shifts
* Colour Texture Segmentation by Region-Boundary Cooperation
* Combined PDE and Texture Synthesis Approach to Inpainting, A
* Combining Geometric- and View-Based Approaches for Articulated Pose Estimation
* Consistency Conditions on the Medial Axis
* Constrained Semi-supervised Learning Approach to Data Association, A
* Constraints on Coplanar Moving Points
* Correlation-Based Approach to Robust Point Set Registration, A
* Coupled-Contour Tracking through Non-orthogonal Projections and Fusion for Echocardiography
* Decision Theoretic Modeling of Human Facial Displays
* Detection and Tracking Scheme for Line Scratch Removal in an Image Sequence
* Dimensionality Reduction by Canonical Contextual Correlation Projections
* Discriminant Analysis on Embedded Manifold
* Dynamic Visual Search Using Inner-Scene Similarity: Algorithms and Inherent Limitations
* Enhancing Particle Filters Using Local Likelihood Sampling
* Estimating Intrinsic Images from Image Sequences with Biased Illumination
* Evaluation of Image Fusion Performance with Visible Differences
* Evaluation of Robust Fitting Based Detection
* Example-Based Stereo with General BRDFs
* Extending Interrupted Feature Point Tracking for 3-D Affine Reconstruction
* Extraction of Semantic Dynamic Content from Videos with Probabilistic Motion Models
* Extrinsic Camera Parameter Recovery from Multiple Image Sequences Captured by an Omni-Directional Multi-camera System
* Face Recognition from Facial Surface Metric
* Face Recognition with Local Binary Patterns
* Fast Object Detection with Occlusions
* Feature-Based Approach for Determining Dense Long Range Correspondences, A
* Fourier Theory for Cast Shadows, A
* Framework for Pencil-of-Points Structure-from-Motion, A
* From a 2D Shape to a String Structure Using the Symmetry Set
* Fusion of Infrared and Visible Images for Face Recognition
* General Linear Cameras
* Generalized Histogram: Empirical Optimization of Low Dimensional Features for Image Matching
* Generic Concept for Camera Calibration, A
* Groupwise Diffeomorphic Non-rigid Registration for Automatic Model Building
* Hand Gesture Recognition within a Linguistics-Based Framework
* Hand Motion from 3D Point Trajectories and a Smooth Surface Model
* Hierarchical Implicit Surface Joint Limits to Constrain Video-Based Motion Capture
* Hierarchical Organization of Shapes for Efficient Retrieval
* High Accuracy Optical Flow Estimation Based on a Theory for Warping
* High-Contrast Color-Stripe Pattern for Rapid Structured-Light Range Imaging
* Human Detection Based on a Probabilistic Assembly of Robust Part Detectors
* Human Pose Estimation Using Learnt Probabilistic Region Similarities and Partial Configurations
* Human Upper Body Pose Estimation in Static Images
* Image and Video Segmentation by Anisotropic Kernel Mean Shift
* Image Anisotropic Diffusion Based on Gradient Vector Flow Fields
* Image Clustering with Metric, Local Linear Structure, and Affine Symmetry
* Image Similarity Using Mutual Information of Regions
* Inferring White Matter Geometry from Diffusion Tensor MRI: Application to Connectivity Mapping
* Information-Based Measure for Grouping Quality, An
* Interactive Image Segmentation Using an Adaptive GMMRF Model
* Interpolating Novel Views from Image Sequences by Probabilistic Depth Carving
* Intrinsic Images by Entropy Minimization
* Iso-disparity Surfaces for General Stereo Configurations
* Joint Bayes Filter: A Hybrid Tracker for Non-rigid Hand Motion Recognition
* Kernel Feature Selection with Side Data Using a Spectral Approach
* Keyframe Selection for Camera Motion and Structure Estimation from Multiple Views
* Kullback-Leibler Kernel as a Framework for Discriminant and Localized Representations for Visual Recognition, The
* Learning Mixtures of Weighted Tree-Unions by Minimizing Description Length
* Learning Outdoor Color Classification from Just One Training Image
* Learning to Segment
* Line Geometry for 3D Shape Understanding and Reconstruction
* Linguistic Feature Vector for the Visual Interpretation of Sign Language, A
* Local Orientation Smoothness Prior for Vascular Segmentation of Angiography
* Many-to-Many Feature Matching Using Spherical Coding of Directed Graphs
* Matching Tensors for Automatic Correspondence and Registration
* MCMC-Based Multiview Reconstruction of Piecewise Smooth Subdivision Curves with a Variable Number of Control Points
* MCMC-Based Particle Filter for Tracking Multiple Interacting Targets, An
* Model Selection for Range Segmentation of Curved Objects
* Modeling and Synthesis of Facial Motion Driven by Speech
* Monocular 3D Reconstruction of Human Motion in Long Action Sequences
* Morphological Operations on Matrix-Valued Images
* Multiple Classifier System Approach to Model Pruning in Object Recognition
* Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis
* Multiscale Inverse Compositional Alignment for Subdivision Surface Maps
* Normalized Cross-Correlation for Spherical Images
* Novel Skeletal Representation for Articulated Creatures
* Object Level Grouping for Video Shots
* Omnidirectional Vision: Unified Model Using Conformal Geometry
* On Refractive Optical Flow
* On the Significance of Real-World Conditions for Material Classification
* Optimal Importance Sampling for Tracking in Image Sequences: Application to Point Tracking
* Parallel Variational Motion Estimation by Domain Decomposition and Cluster Computing
* Partial Object Matching with Shapeme Histograms
* PDE Solution of Brownian Warping, A
* Polynomial-Time Metric for Attributed Trees, A
* Pose Estimation of Free-Form Objects
* Probabilistic Multi-view Correspondence in a Distributed Setting with No Central Server
* Quality of Catadioptric Imaging: Application to Omnidirectional Stereo, The
* Real-Time Tracking of Multiple Skin-Colored Objects with a Possibly Moving Camera
* Recognition by Probabilistic Hypothesis Construction
* Recognizing Objects in Range Data Using Regional Point Descriptors
* Reconstruction from Projections Using Grassmann Tensors
* Reconstruction of 3-D Symmetric Curves from Perspective Images without Discrete Features
* Recovering Local Shape of a Mirror Surface from Reflection of a Regular Grid
* Region-Based Segmentation on Evolving Surfaces with Application to 3D Reconstruction of Shape and Piecewise Constant Radiance
* Reliable Fiducial Detection in Natural Scenes
* Robust Algorithm for Characterizing Anisotropic Local Structures, A
* Robust Fitting by Adaptive-Scale Residual Consensus
* Robust Probabilistic Estimation Framework for Parametric Image Models, A
* Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion
* Seamless Image Stitching in the Gradient Domain
* Semantics Discovery for Image Indexing
* Separating Specular, Diffuse, and Subsurface Scattering Reflectances from Photometric Images
* Separating Transparent Layers through Layer Information Exchange
* Shape Matching and Recognition: Using Generative Models and Informative Features
* Shape Reconstruction from 3D and 2D Data Using PDE-Based Deformable Surfaces
* Simultaneous Object Recognition and Segmentation by Image Exploration
* Sparse Finite Elements for Geodesic Contours with Level-Sets
* Spatially Homogeneous Dynamic Textures
* Spectral Clustering for Robust Motion Segmentation
* Spectral Simplification of Graphs
* Spectral Solution of Large-Scale Extrinsic Camera Calibration as a Graph Embedding Problem
* Statistical Model for General Contextual Object Recognition, A
* Steering in Scale Space to Optimally Detect Image Structures
* Stereovision-Based Head Tracking Using Color and Ellipse Fitting in a Particle Filter
* Stitching and Reconstruction of Linear-Pushbroom Panoramic Images for Planar Scenes
* Stretching Bayesian Learning in the Relevance Feedback of Image Retrieval
* Structure and Motion from Images of Smooth Textureless Objects
* Structure and Motion Problems for Multiple Rigidly Moving Cameras
* Structure from Motion of Parallel Lines
* Structure of Applicable Surfaces from Single Views
* Support Blob Machines: The Sparsification of Linear Scale Space
* Surface Reconstruction by Propagating 3D Stereo Data in Multiple 2D Images
* Temporal Factorization vs. Spatial Factorization
* Tensor Field Segmentation Using Region Based Active Contour Model
* Texton Correlation for Recognition
* Texture Boundary Detection for Real-Time Tracking
* Topology Preserving Non-rigid Registration Method Using a Symmetric Similarity Function-Application to 3-D Brain Images, A
* Toward Accurate Segmentation of the LV Myocardium and Chamber for Volumes Estimation in Gated SPECT Sequences
* Towards Intelligent Mission Profiles of Micro Air Vehicles: Multiscale Viterbi Classification
* Tracking Articulated Motion Using a Mixture of Autoregressive Models
* Tracking Aspects of the Foreground against the Background
* TV Flow Based Local Scale Measure for Texture Discrimination, A
* Unified Algebraic Approach to 2-D and 3-D Motion Segmentation, A
* Unifying Approaches and Removing Unrealistic Assumptions in Shape from Shading: Mathematics Can Help
* User Assisted Separation of Reflections from a Single Image Using a Sparsity Prior
* Using Inter-feature-Line Consistencies for Sequence-Based Object Recognition
* Variational Pairing of Image Segmentation and Blind Restoration
* View-Invariant Recognition Using Corresponding Object Fragments
* Visibility Analysis and Sensor Planning in Dynamic Environments
* Visual Category Filter for Google Images, A
* Weak Hypotheses and Boosting for Generic Object Detection and Recognition
* Weighted Minimal Hypersurfaces and Their Applications in Computer Vision
* What Do Four Points in Two Calibrated Images Tell Us about the Epipoles?
* Whitening for Photometric Comparison of Smooth Surfaces under Varying Illumination
171 for ECCV04

ECCV06 * *ECCV
* 2D and 3D Multimodal Hybrid Face Recognition
* 3D Surface Reconstruction Using Graph Cuts with Surface Constraints
* 4-Source Photometric Stereo Under General Unknown Lighting, The
* Accelerated Convergence Using Dynamic Mean Shift
* Adapted Vocabularies for Generic Visual Categorization
* Affine Invariant of Parallelograms and Its Application to Camera Calibration and 3D Reconstruction, An
* Affine-Invariant Multi-reference Shape Priors for Active Contours
* Algebraic Methods for Direct and Feature Based Registration of Diffusion Tensor Images
* Alias-Free Interpolation
* Automatic Image Segmentation by Positioning a Seed
* Background Cut
* Balanced Exploration and Exploitation Model Search for Efficient Epipolar Geometry Estimation
* Bilateral Filtering-Based Optical Flow Estimation with Occlusion Detection
* Blind Vision
* Boundary-Fragment-Model for Object Detection, A
* Camera Calibration with Two Arbitrary Coaxial Circles
* Carved Visual Hulls for Image-Based Modeling
* Coloring Local Feature Extraction
* Comparative Study of Energy Minimization Methods for Markov Random Fields, A
* Comparison of Energy Minimization Algorithms for Highly Connected Graphs
* Conditional Infomax Learning: An Integrated Framework for Feature Extraction and Fusion
* Confocal Stereo
* Context-Aided Human Recognition: Clustering
* Controlling Sparseness in Non-negative Tensor Factorization
* Covariant Derivatives and Vision
* Curvature-Preserving Regularization of Multi-valued Images Using PDE's
* Cyclostationary Processes on Shape Spaces for Gait-Based Recognition
* Database-Guided Simultaneous Multi-slice 3D Segmentation for Volumetric Data
* Defocus Inpainting
* Degen Generalized Cylinders and Their Properties
* Dense Photometric Stereo by Expectation Maximization
* Density Estimation Using Mixtures of Mixtures of Gaussians
* Describing and Matching 2D Shapes by Their Points of Mutual Symmetry
* Detecting Doctored JPEG Images Via DCT Coefficient Analysis
* Detecting Instances of Shape Classes That Exhibit Variable Structure
* Detecting Symmetry and Symmetric Constellations of Features
* Differential Geometric Consistency Extends Stereo to Curved Surfaces
* Direct Energy Minimization for Super-Resolution on Nonlinear Manifolds
* Direct Solutions for Computing Cylinders from Minimal Sets of 3D Points
* Discovering Texture Regularity as a Higher-Order Correspondence Problem
* Efficient Belief Propagation with Learned Higher-Order Markov Random Fields
* Efficient Method for Tensor Voting Using Steerable Filters, An
* Ellipse Fitting with Hyperaccuracy
* EMD-L1: An Efficient and Robust Algorithm for Comparing Histogram-Based Descriptors
* Enhancing the Point Feature Tracker by Adaptive Modelling of the Feature Support
* Estimating Gaze Direction from Low-Resolution Faces in Video
* Estimation of Multiple Periodic Motions from Video
* Euclidean Structure from N^2 Parallel Circles: Theory and Algorithms
* Example Based Non-rigid Shape Detection
* Exploiting Model Similarity for Indexing and Matching to a Large Model Database
* Extending Kernel Fisher Discriminant Analysis with the Weighted Pairwise Chernoff Criterion
* Face Authentication Using Adapted Local Binary Pattern Histograms
* Face Recognition from Video Using the Generic Shape-Illumination Manifold
* Fast Approximation of the Bilateral Filter Using a Signal Processing Approach, A
* Fast Line Segment Based Dense Stereo Algorithm Using Tree Dynamic Programming, A
* Fast Memory-Efficient Generalized Belief Propagation
* Fast, Quality, Segmentation of Large Volumes: Isoperimetric Distance Trees
* Feature Points Tracking: Robustness to Specular Highlights and Lighting Changes
* Figure/Ground Assignment in Natural Images
* Fluid Motion Estimator for Schlieren Image Velocimetry, A
* From Tensor-Driven Diffusion to Anisotropic Wavelet Shrinkage
* Gait Recognition Using a View Transformation Model in the Frequency Domain
* General Framework for Motion Segmentation: Independent, Articulated, Rigid, Non-rigid, Degenerate and Non-degenerate, A
* Generalized Multi-sensor Planning
* Geodesics Between 3D Closed Curves Using Path-Straightening
* Geometry and Kinematics with Uncertain Data
* Globally Optimal Active Contours, Sequential Monte Carlo and On-Line Learning for Vessel Segmentation
* High Accuracy Optical Flow Serves 3-D Pose Tracking: Exploiting Contour and Flow Based Constraints
* Higher Order Image Pyramids
* Human Detection Using Oriented Histograms of Flow and Appearance
* Human Pose Tracking Using Multi-level Structured Models
* Hyperfeatures: Multilevel Local Coding for Visual Recognition
* Identification of Highly Similar 3D Objects Using Model Saliency
* Image Specific Feature Similarities
* Incorporating Non-motion Cues into 3D Motion Segmentation
* Integral Solution to Surface Evolution PDEs Via Geo-cuts, An
* Integrated Model for Accurate Shape Alignment, An
* Integrating Surface Normal Vectors Using Fast Marching Method
* Intensity Similarity Measure in Low-Light Conditions, An
* Inter-modality Face Recognition
* Interpolating Orientation Fields: An Axiomatic Approach
* Iterative Extensions of the Sturm/Triggs Algorithm: Convergence and Nonconvergence
* Kernel-Predictability: A New Information Measure and Its Application to Image Registration
* Learning 2D Hand Shapes Using the Topology Preservation Model GNG
* Learning and Incorporating Top-Down Cues in Image Segmentation
* Learning Based Approach for 3D Segmentation and Colon Detagging, A
* Learning Compositional Categorization Models
* Learning Discriminative Canonical Correlations for Object Recognition with Image Sets
* Learning Effective Intrinsic Features to Boost 3D-Based Face Recognition
* Learning Nonlinear Manifolds from Time Series
* Learning Semantic Scene Models by Trajectory Analysis
* Learning to Combine Bottom-Up and Top-Down Segmentation
* Learning to Detect Objects of Many Classes Using Binary Classifiers
* Located Hidden Random Fields: Learning Discriminative Parts for Object Detection
* Machine Learning for High-Speed Corner Detection
* Maximally Stable Local Description for Scale Selection
* Measuring Uncertainty in Graph Cut Solutions: Efficiently Computing Min-marginal Energies Using Dynamic Graph Cuts
* Modeling 3D Objects from Stereo Views and Recognizing Them in Photographs
* Molding Face Shapes by Example
* Monocular Tracking of 3D Human Motion with a Coordinated Mixture of Factor Analyzers
* Multi-camera Tracking and Segmentation of Occluded People on Ground Plane Using Search-Guided Particle Filtering
* Multi-way Clustering Using Super-Symmetric Non-negative Tensor Factorization
* Multiclass Image Labeling with Semidefinite Programming
* Multivalued Default Logic for Identity Maintenance in Visual Surveillance
* Multivariate Relevance Vector Machines for Tracking
* Multiview Approach to Tracking People in Crowded Scenes Using a Planar Homography Constraint, A
* New 3-D Model Retrieval System Based on Aspect-Transition Descriptor, A
* Non Linear Temporal Textures Synthesis: A Monte Carlo Approach
* Nonrigid Shape and Motion from Multiple Perspective Views
* Object Detection by Contour Segment Networks
* Optimal Multi-frame Correspondence with Assignment Tensors
* Oriented Visibility for Multiview Reconstruction
* Overconstrained Linear Estimation of Radial Distortion and Multi-view Geometry
* Patch-Based Texture Edges and Segmentation
* Perspective n-View Multibody Structure-and-Motion Through Model Selection
* Physically-Motivated Deformable Model Based on Fluid Dynamics, A
* PoseCut: Simultaneous Segmentation and 3D Pose Estimation of Humans Using Dynamic Graph-Cuts
* Practical Global Optimization for Multiview Geometry
* Probabilistic Linear Discriminant Analysis
* Random Walks, Constrained Multiple Hypothesis Testing and Image Enhancement
* Real-Time Non-rigid Shape Recovery Via Active Appearance Models for Augmented Reality
* Real-Time Upper Body Detection and 3D Pose Estimation in Monoscopic Images
* Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost
* Reconstruction of Canal Surfaces from Single Images Under Exact Perspective
* Region Covariance: A Fast Descriptor for Detection and Classification
* Resolution-Aware Fitting of Active Appearance Models to Low Resolution Images
* Resolution-Enhanced Photometric Stereo
* Retexturing Single Views Using Texture and Shading
* Revisiting the Brightness Constraint: Probabilistic Formulation and Algorithms
* Riemannian Manifold Learning for Nonlinear Dimensionality Reduction
* Robust and Efficient Photo-Consistency Estimation for Volumetric 3D Reconstruction
* Robust Attentive Behavior Detection by Non-linear Head Pose Embedding and Estimation
* Robust Expression-Invariant Face Recognition from Partially Missing Data
* Robust Homography Estimation from Planar Contours Based on Convexity
* Robust Multi-body Motion Tracking Using Commute Time Clustering
* Robust Multi-view Face Detection Using Error Correcting Output Codes
* Robust Player Gesture Spotting and Recognition in Low-Resolution Sports Video
* Robust Visual Tracking for Multiple Targets
* Sampling Representative Examples for Dimensionality Reduction and Recognition: Bumping LDA
* Sampling Strategies for Bag-of-Features Image Classification
* Scene Classification Via pLSA
* Segmentation of High Angular Resolution Diffusion MRI Modeled as a Field of von Mises-Fisher Mixtures
* Segmenting Highly Articulated Video Objects with Weak-Prior Random Forests
* Self-calibration of a General Radially Symmetric Distortion Model
* Shape Analysis and Fuzzy Control for 3D Competitive Segmentation of Brain Structures with Level Sets
* Shape-from-Silhouette with Two Mirrors and an Uncalibrated Camera
* Shift-Invariant Dynamic Texture Recognition
* Simple Solution to the Six-Point Two-View Focal-Length Problem, A
* Simultaneous Object Pose and Velocity Computation Using a Single View from a Rolling Shutter Camera
* Smooth Image Segmentation by Nonparametric Bayesian Inference
* Space-Time-Scale Registration of Dynamic Scene Reconstructions
* Sparse Flexible Models of Local Features
* SpatialBoost: Adding Spatial Reasoning to AdaBoost
* Spatio-temporal Embedding for Statistical Face Recognition from Video
* Specularity Removal in Images and Videos: A PDE Approach
* Statistical Priors for Efficient Combinatorial Optimization Via Graph Cuts
* Studying Aesthetics in Photographic Images Using a Computational Approach
* Subspace Estimation Using Projection Based M-Estimators over Grassmann Manifolds
* Super-Resolution of 3D Face
* SURF: Speeded Up Robust Features
* TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation
* Theory of Multiple Orientation Estimation, A
* Theory of Spherical Harmonic Identities for BRDF/Lighting Transfer and Image Consistency, A
* Top-Points as Interest Points for Image Matching
* Towards Optimal Training of Cascaded Detectors
* Towards Safer, Faster Prenatal Genetic Tests: Novel Unsupervised, Automatic and Robust Methods of Segmentation of Nuclei and Probes
* Trace Quotient Problems Revisited
* Tracking Dynamic Near-Regular Texture Under Occlusion and Rapid Movements
* Tracking Objects Across Cameras by Incrementally Learning Inter-camera Colour Calibration and Patterns of Activity
* Triangulation for Points on Lines
* Tuned Eigenspace Technique for Articulated Motion Recognition, A
* Uncalibrated Factorization Using a Variable Symmetric Affine Camera
* Unifying Framework for Mutual Information Methods for Use in Non-linear Optimisation, A
* Unsupervised Patch-Based Image Regularization and Representation
* Unsupervised Texture Segmentation with Nonparametric Neighborhood Statistics
* Variational Motion Segmentation with Level Sets
* Variational Shape and Reflectance Estimation Under Changing Light and Viewpoints
* Video and Image Bayesian Demosaicing with a Two Color Image Prior
* Video Mensuration Using a Stationary Camera
* Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions
* Wavelet-Based Super-Resolution Reconstruction: Theory and Algorithm
* Weakly Supervised Learning of Part-Based Spatial Models for Visual Object Recognition
* What Is the Range of Surface Reconstructions from a Gradient Field?
184 for ECCV06

ECCV08 * *ECCV
* 2D Image Analysis by Generalized Hilbert Transforms in Conformal Space
* 3D Face Model Fitting for Recognition
* 3D Face Recognition by Local Shape Difference Boosting
* 3D Non-rigid Surface Matching and Registration Based on Holomorphic Differentials
* Action Recognition with a Bio-inspired Feedforward Motion Processing Model: The Richness of Center-Surround Interactions
* Active Contour Based Segmentation of 3D Surfaces
* Active Image Labeling and Its Application to Facial Action Labeling
* Active Matching
* Analysis of Building Textures for Reconstructing Partially Occluded Facades
* Anisotropic Geodesics for Perceptual Grouping and Domain Meshing
* Articulated Multi-body Tracking under Egomotion
* ASN: Image Keypoint Detection from Adaptive Shape Neighborhood
* Automated Delineation of Dendritic Networks in Noisy Image Stacks
* Automatic Generator of Minimal Problem Solvers
* Automatic Image Colorization Via Multimodal Predictions
* Background Subtraction on Distributions
* Behind the Depth Uncertainty: Resolving Ordinal Depth in SFM
* Belief Propagation with Directional Statistics for Solving the Shape-from-Shading Problem
* Beyond Loose LP-Relaxations: Optimizing MRFs by Repairing Cycles
* Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers
* Bi-directional Framework for Unifying Parametric Image Alignment Approaches, The
* Brain Hallucination
* Building a Compact Relevant Sample Coverage for Relevance Feedback in Content-Based Image Retrieval
* Calibration from Statistical Properties of the Visual World
* Cat Head Detection: How to Effectively Exploit Shape and Texture Features
* CenSurE: Center Surround Extremas for Realtime Feature Detection and Matching
* Closed-Form Solution to Non-rigid 3D Surface Registration
* Co-recognition of Image Pairs by Data-Driven Monte Carlo Image Exploration
* Column-Pivoting Based Strategy for Monomial Ordering in Numerical Gröbner Basis Calculations, A
* Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus, A
* Compressive Sensing for Background Subtraction
* Compressive Structured Light for Recovering Inhomogeneous Participating Media
* Constrained Maximum Likelihood Learning of Bayesian Networks for Facial Action Recognition
* Constructing Category Hierarchies for Visual Recognition
* Continuous Energy Minimization Via Repeated Binary Fusion
* Contour Context Selection for Object Detection: A Set-to-Set Contour Matching Approach
* Convex Formulation of Continuous Multi-label Problems, A
* Cross-View Action Recognition from Temporal Self-similarities
* CSDD Features: Center-Surround Distribution Distance for Feature Extraction and Matching
* Deformed Lattice Discovery Via Efficient Mean-Shift Belief Propagation
* Detecting Carried Objects in Short Video Sequences
* Determining Patch Saliency Using Low-Level Context
* Differential Spatial Resection: Pose Estimation Using a Single Local Image Feature
* Direct Bundle Estimation for Recovery of Shape, Reflectance Property and Light Position
* Discriminative Learning for Deformable Shape Segmentation: A Comparative Study
* Discriminative Locality Alignment
* Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation
* Dynamic Conditional Random Field Model for Joint Labeling of Object and Scene Classes, A
* Dynamic Integration of Generalized Cues for Person Tracking
* Edge-Preserving Smoothing and Mean-Shift Segmentation of Video Streams
* Effective Approach to 3D Deformable Surface Tracking, An
* Efficient Camera Smoothing in Sequential Structure-from-Motion Using Approximate Cross-Validation
* Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector, An
* Efficient Dense Scene Flow from Sparse or Dense Stereo Data
* Efficient Edge-Based Methods for Estimating Manhattan Frames in Urban Imagery
* Efficient NCC-Based Image Matching in Walsh-Hadamard Domain
* Efficiently Learning Random Fields for Stereo Vision with Sparse Message Passing
* Estimating 3D Face Model and Facial Deformation from a Single Image Based on Expression Manifold Optimization
* Estimating 3D Trajectories of Periodic Motions from Stationary Monocular Views
* Estimating Geo-temporal Location of Stationary Cameras Using Shadow Trajectories
* Estimating Radiometric Response Functions from Image Noise Variance
* Event Modeling and Recognition Using Markov Logic Networks
* Experimental Comparison of Discrete and Continuous Shape Optimization Methods, An
* Extended Phase Field Higher-Order Active Contour Model for Networks and Its Application to Road Network Extraction from VHR Satellite Images, An
* Extracting Moving People from Internet Videos
* Face Alignment Via Component-Based Discriminative Search
* FaceTracer: A Search Engine for Large Collections of Images with Faces
* Facial Expression Recognition Based on 3D Dynamic Range Model Sequences
* Fast Algorithm for Creating a Compact and Discriminative Visual Codebook, A
* Fast and Accurate Rotation Estimation on the 2-Sphere without Correspondences
* Fast Automatic Single-View 3-d Reconstruction of Urban Scenes
* Feature Correspondence Via Graph Matching: Models and Global Optimization
* Finding Actions Using Shape Flows
* Flexible Depth of Field Photography
* Floor Fields for Tracking in High Density Crowd Scenes
* Fourier Analysis of the 2D Screened Poisson Equation for Gradient Domain Problems
* Fusion of Feature- and Area-Based Information for Urban Buildings Modeling from Aerial Imagery
* General Imaging Geometry for Central Catadioptric Cameras
* Generative Image Segmentation Using Random Walks with Restart
* Generative Shape Regularization Model for Robust Face Alignment, A
* Generic Neighbourhood Filtering Framework for Matrix Fields, A
* GeoS: Geodesic Image Segmentation
* Graph Based Subspace Semi-supervised Learning Framework for Dimensionality Reduction, A
* Grassmann Registration Manifolds for Face Recognition
* Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search
* Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features
* Higher-Dimensional Affine Registration and Vision Applications
* Human Activity Recognition with Metric Learning
* Illumination and Person-Insensitive Head Pose Estimation Using Distance Metric Learning
* Image Feature Extraction Using Gradient Local Auto-Correlations
* Image Segmentation by Branch-and-Mincut
* Image Segmentation in the Presence of Shadows and Highlights
* Implementing Decision Trees and Forests on a GPU
* Improving People Search Using Query Expansions: How Friends Help to Find People
* Improving Shape Retrieval by Learning Graph Transduction
* Improving the Agility of Keyframe-Based SLAM
* Incremental Learning Method for Unconstrained Gaze Estimation, An
* Integration of Multiview Stereo and Silhouettes Via Convex Functionals on Convex Domains
* Interactive Tracking of 2D Generic Objects with Spacetime Optimization
* Joint Parametric and Non-parametric Curve Evolution for Medical Image Segmentation
* Kernel Codebooks for Scene Categorization
* Key Object Driven Multi-category Object Recognition, Localization and Tracking Using Spatio-temporal Context
* Keypoint Signatures for Fast Learning and Recognition
* Latent Pose Estimator for Continuous Action Recognition
* Lattice-Preserving Multigrid Method for Solving the Inhomogeneous Poisson Equations Used in Image Analysis, A
* Learning CRFs Using Graph Cuts
* Learning for Optical Flow Using Stochastic Optimization
* Learning from Real Images to Model Lighting Variations for Face Images
* Learning Optical Flow
* Learning Spatial Context: Using Stuff to Find Things
* Learning to Localize Objects with Structured Output Regression
* Learning to Recognize Activities from the Wrong View Point
* Learning Two-View Stereo Matching
* Learning Visual Shape Lexicon for Document Image Content Recognition
* Light-Efficient Photography
* Linear Time Histogram Metric for Improved SIFT Matching, A
* Linear Time Maximally Stable Extremal Regions
* Linking Pose and Motion
* Local Regularization for Multiclass Classification Facing Significant Intraclass Variations
* Local Statistic Based Region Segmentation with Automatic Scale Selection
* Localizing Objects with Smart Dictionaries
* Locating Facial Features with an Extended Active Shape Model
* Making Background Subtraction Robust to Sudden Illumination Changes
* Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs .
* Motion Context: A New Representation for Human Action Recognition
* Movie/Script: Alignment and Parsing of Video and Text Transcription
* Multi-camera Tracking and Atypical Motion Detection with Behavioral Maps
* Multi-layered Decomposition of Recurrent Scenes
* Multi-scale Improves Boundary Detection in Natural Images
* Multi-scale Vector Spline Method for Estimating the Fluids Motion on Satellite Images, A
* Multi-stage Contour Based Detection of Deformable Objects
* Multi-thread Parsing for Recognizing Complex Events in Videos
* Multiple Component Learning for Object Detection
* Multiple Instance Boost Using Graph Embedding Based Decision Stump for Pedestrian Detection
* Multiple Tree Models for Occlusion and Spatial Constraints in Human Pose Estimation
* Naked Truth: Estimating Body Shape Under Clothing, The
* New Baseline for Image Annotation, A
* Non-local Regularization of Inverse Problems
* Nonrigid Image Registration Using Dynamic Higher-Order MRF Model
* Object Detection from Large-Scale 3D Datasets Using Bottom-Up and Top-Down Descriptors
* Object Recognition by Integrating Multiple Image Segmentations
* Online Sparse Matrix Gaussian Process Regression and Vision Applications
* Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers
* Optimization of Symmetric Transfer Error for Sub-frame Video Synchronization
* Optimizing Binary MRFs with Higher Order Cliques
* Output Regularized Metric Learning with Side Information
* Partial Difference Equations over Graphs: Morphological Processing of Arbitrary Discrete Data
* Passive Reflectometry
* Perceptual Comparison of Distance Measures for Color Constancy Algorithms, A
* Perspective Nonrigid Shape and Motion Recovery
* Photo and Video Quality Evaluation: Focusing on the Subject
* Pose Priors for Simultaneously Solving Alignment and Correspondence
* Pose-Invariant Descriptor for Human Detection and Segmentation, A
* Prior-Based Piecewise-Smooth Segmentation by Template Competitive Deformation Using Partitions of Unity
* Priors for Large Photo Collections and What They Reveal about Cameras
* Probabilistic Approach to Integrating Multiple Cues in Visual Tracking, A
* Probabilistic Cascade of Detectors for Individual Object Recognition, A
* Projected Texture for Object Classification
* Quick Shift and Kernel Methods for Mode Seeking
* Range Flow for Varying Illumination
* Rank Classification of Linear Line Structure in Determining Trifocal Tensor
* Real Time Feature Based 3-D Deformable Face Tracking
* Real-Time Shape Analysis of a Human Body in Clothing Using Time-Series Part-Labeled Volumes
* Recovering Light Directions and Camera Poses from a Single Sphere
* Reformulating and Optimizing the Mumford-Shah Functional on a Graph: A Faster, Lower Energy Solution
* Region-Based 2D Deformable Generalized Cylinder for Narrow Structures Segmentation
* Regular Texture Analysis as Statistical Model Selection
* Regularized Partial Matching of Rigid Shapes
* Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images
* Riemannian Anisotropic Diffusion for Tensor Valued Images
* Robust 3D Pose Estimation and Efficient 2D Region-Based Segmentation from a 3D Shape Prior
* Robust Multiple Structures Estimation with J-Linkage
* Robust Object Tracking by Hierarchical Association of Detection Responses
* Robust Optimal Pose Estimation
* Robust Real-Time Visual Tracking Using Pixel-Wise Posteriors
* Robust Scale Estimation from Ensemble Inlier Sets for Random Sample Consensus Methods
* Robust Visual Tracking Based on an Effective Appearance Model
* Saliency Based Opportunistic Search for Object Part Extraction and Labeling
* Sample Sufficiency and PCA Dimension for Statistical Shape Models
* Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners
* Scale-Dependent/Invariant Local 3D Shape Descriptors for Fully Automatic Registration of Multiple Sets of Range Images
* Scene Discovery by Matrix Factorization
* Scene Segmentation for Behaviour Correlation
* Scene Segmentation Using the Wisdom of Crowds
* Search Space Reduction for MRF Stereo
* Searching the World's Herbaria: A System for Visual Identification of Plant Species
* Segmentation and Recognition Using Structure from Motion Point Clouds
* Segmentation Based Variational Model for Accurate Optical Flow Estimation, A
* Segmenting Fiber Bundles in Diffusion Tensor Images
* Semantic Concept Classification by Joint Semi-supervised Learning of Feature Subspaces and Support Vector Machines
* Semi-automatic Motion Segmentation with Motion Layer Mosaics
* Semi-supervised On-Line Boosting for Robust Tracking
* Semidefinite Programming Heuristics for Surface Reconstruction Ambiguities
* SERBoost: Semi-supervised Boosting with Expectation Regularization
* Shadows in Three-Source Photometric Stereo
* Shape Matching by Segmentation Averaging
* Shape-Based Retrieval of Heart Sounds for Disease Similarity Detection
* SIFT Flow: Dense Correspondence across Different Scenes
* Signature-Based Document Image Retrieval
* Similarity Features for Facial Event Analysis
* Simultaneous Detection and Registration for Ileo-Cecal Valve Detection in 3D CT Colonography
* Simultaneous Motion Detection and Background Reconstruction with a Mixed-State Conditional Markov Random Field
* Simultaneous Visual Recognition of Manipulation Actions and Manipulated Objects
* SMD: A Locally Stable Monotonic Change Invariant Feature Descriptor
* Solving Image Registration Problems Using Interior Point Methods
* Some Objects Are More Equal Than Others: Measuring and Predicting Importance
* Something Old, Something New, Something Borrowed, Something Blue
* Sparse Long-Range Random Field and Its Application to Image Denoising
* Sparse Structures in L-Infinity Norm Minimization for Structure and Motion Reconstruction
* Star Shape Prior for Graph-Cut Image Segmentation
* Statistical Analysis of Global Motion Chains
* Statistical Confidence Measure for Optical Flows, A
* Stereo Matching: An Outlier Confidence Approach
* Structuring Visual Words in 3D for Arbitrary-View Object Localization
* Student-t Mixture Filter for Robust, Real-Time Visual Tracking
* Surface Visibility Probabilities in 3D Cluttered Scenes
* Temporal Dithering of Illumination for Fast Active Vision
* Temporal Surface Tracking Using Mesh Evolution
* Texture-Consistent Shadow Removal
* Three Dimensional Curvilinear Structure Detection Using Optimally Oriented Flux
* Toward Global Minimum through Combined Local Minima
* Towards Scalable Dataset Construction: An Active Learning Approach
* Tracking of Abrupt Motion Using Wang-Landau Monte Carlo Estimation
* Tracking with Dynamic Hidden-State Shape Models
* Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks
* Understanding Camera Trade-Offs through a Bayesian Analysis of Light Field Projections
* Unified Crowd Segmentation
* Unified Frequency Domain Analysis of Lightfield Cameras
* Unsupervised Classification and Part Localization by Consistency Amplification
* Unsupervised Learning of Skeletons from Motion
* Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion
* Using 3D Line Segments for Robust and Efficient Change Detection from Multiple Noisy Images
* Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo
* Video Registration Using Dynamic Textures
* VideoCut: Removing Irrelevant Frames by Discovering the Object of Interest
* View Point Tracking of Rigid Objects Based on Shape Sub-manifolds
* View Synthesis for Recognizing Unseen Poses of Object Classes
* Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features
* Vision-Based Multiple Interacting Targets Tracking via On-Line Supervised Learning
* Weakly Supervised Object Localization with Stable Segmentations
* What Does the Sky Tell Us about the Camera?
* What Is a Good Image Segment? A Unified Approach to Segment Extraction
* What Is a Good Nearest Neighbors Algorithm for Finding Similar Patches in Images?
* Window Annealing over Square Lattice Markov Random Field
245 for ECCV08

ECCV10 * *ECCV
* 2.5D Dual Contouring: A Robust Approach to Creating Building Models from Aerial LiDAR Point Clouds
* 2D Action Recognition Serves 3D Human Pose Estimation
* 2D Human Body Model Dressed in Eigen Clothing, A
* 3D Deformable Face Tracking with a Commodity Depth Camera
* 3D Point Correspondence by Minimum Description Length in Feature Space
* 3D Reconstruction of a Moving Point from a Series of 2D Projections
* 5D Motion Subspaces for Planar Motions
* Accelerated Hypothesis Generation for Multi-structure Robust Fitting
* Accurate Image Localization Based on Google Maps Street View
* Active Mask Hierarchies for Object Detection
* Activities as Time Series of Human Postures
* Adapting Visual Category Models to New Domains
* Adaptive and Generic Corner Detection Based on the Accelerated Segment Test
* Adaptive Metric Registration of 3D Models to Non-rigid Image Trajectories
* Adaptive Regularization for Image Segmentation Using Local Image Curvature Cues
* ADICT: Accurate Direct and Inverse Color Transformation
* Affine Puzzle: Realigning Deformed Object Fragments without Correspondences
* Aligning Spatio-Temporal Signals on a Special Manifold
* Ambrosio-Tortorelli Segmentation of Stochastic Images
* Analysis of Motion Blur with a Flutter Shutter Camera for Non-linear Motion
* Analytical Forward Projection for Axial Non-central Dioptric and Catadioptric Cameras
* Analyzing Depth from Coded Aperture Sets
* Anisotropic Minimal Surfaces Integrating Photoconsistency and Normal Information for Multiview Stereo
* Anomalous Behaviour Detection Using Spatiotemporal Oriented Energies, Subset Inclusion Histogram Comparison and Event-Driven Processing
* Archive Film Restoration Based on Spatiotemporal Random Walks
* Articulation-Invariant Representation of Non-planar Shapes
* Attribute-Based Transfer Learning for Object Categorization with Zero/One Training Example
* Automated 3D Reconstruction and Segmentation from Optical Coherence Tomography
* Automatic Attribute Discovery and Characterization from Noisy Web Data
* Automatic Learning of Background Semantics in Generic Surveilled Scenes
* Avoiding Confusing Features in Place Recognition
* Backprojection Revisited: Scalable Multi-view Object Detection and Similarity Metrics for Detections
* Balancing Deformability and Discriminability for Shape Matching
* Being John Malkovich
* Bilinear Factorization via Augmented Lagrange Multipliers
* Bilinear Kernel Reduced Rank Regression for Facial Expression Synthesis
* Binary Coherent Edge Descriptors
* Blind Reflectometry
* Blocks World Revisited: Image Understanding Using Qualitative Geometry and Mechanics
* Boosting Chamfer Matching by Learning Chamfer Distance Normalization
* Boundary Detection Using F-Measure-, Filter- and Feature- (F3) Boost
* BRIEF: Binary Robust Independent Elementary Features
* Building Compact Local Pairwise Codebook with Joint Feature Space Clustering
* Building Rome on a Cloudless Day
* Bundle Adjustment in the Large
* Camera Pose Estimation Using Images of Planar Mirror Reflections
* Cascaded Confidence Filtering for Improved Tracking-by-Detection
* Cascaded Models for Articulated Pose Estimation
* Category Independent Object Proposals
* Chrono-Gait Image: A Novel Temporal Template for Gait Recognition
* ClassCut for Unsupervised Class Segmentation
* Close-Form Iterative Algorithm for Depth Inferring from a Single Image, A
* Closed-Loop Adaptation for Robust Tracking
* Clustering Complex Data with Group-Dependent Feature Selection
* Co-transduction for Shape Retrieval
* Coarse-to-Fine Taxonomy of Constellations for Fast Multi-class Object Detection, A
* Colorization for Single Image Super Resolution
* Combining Geometric and Appearance Priors for Robust Homography Estimation
* Compact Video Description for Copy Detection with Precise Temporal Alignment
* Compressive Acquisition of Dynamic Scenes
* Conjugate Gradient Bundle Adjustment
* Constrained Spectral Clustering via Exhaustive and Efficient Constraint Propagation
* Content-Based Retrieval of Functional Objects in Video Using Scene Context
* Continuous Max-Flow Approach to Potts Model, A
* Contour Grouping and Abstraction Using Simple Part Models
* Converting Level Set Gradients to Shape Gradients
* Convex Relaxation for Multilabel Problems with Product Label Spaces
* Convolutional Learning of Spatio-temporal Features
* Correlation-Based Intrinsic Image Extraction from a Single Image
* Cosegmentation Revisited: Models and Optimization
* Coupled Gaussian Process Regression for Pose-Invariant Facial Expression Recognition
* Critical Nets and Beta-Stable Features for Image Matching
* Crowd Detection with a Multiview Sampler
* Data-Driven Approach for Event Prediction, A
* Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow
* Dense, Robust, and Accurate Motion Field Estimation from Stereo Image Sequences in Real-Time
* Depth-Encoded Hough Voting for Joint Object Detection and Shape Recovery
* Descattering Transmission via Angular Filtering
* Descriptor Learning for Efficient Retrieval
* Detecting Faint Curved Edges in Noisy Images
* Detecting Ground Shadows in Outdoor Consumer Photographs
* Detecting Large Repetitive Structures with Salient Boundaries
* Detecting People Using Mutually Consistent Poselet Activations
* Detection and Tracking of Large Number of Targets in Wide Area Surveillance
* Deterministic 3D Human Pose Estimation Using Rigid Structure
* Discovering Multipart Appearance Models from Captioned Images
* Discriminative Latent Model of Object Classes and Attributes, A
* Discriminative Learning with Latent Variables for Cluttered Indoor Scene Understanding
* Discriminative Learning with Latent Variables for Cluttered Indoor Scene Understanding
* Discriminative Mixture-of-Templates for Viewpoint Classification
* Discriminative Nonorthogonal Binary Subspace Tracking
* Discriminative Spatial Attention for Robust Tracking
* Discriminative Tracking by Metric Learning
* Disparity Statistics for Pedestrian Detection: Combining Appearance, Motion and Stereo
* Dual Theory of Inverse and Forward Light Transport, A
* Dynamic Color Flow: A Motion-Adaptive Color Model for Object Segmentation in Video
* Dynamic Programming Approach to Reconstructing Building Interiors, A
* Efficient Computation of Scale-Space Features for Deformable Shape Correspondences
* Efficient Graph Cut Algorithm for Computer Vision Problems, An
* Efficient Highly Over-Complete Sparse Coding Using a Mixture Model
* Efficient Inference with Multiple Heterogeneous Part Detectors for Human Pose Estimation
* Efficient Non-consecutive Feature Tracking for Structure-from-Motion
* Efficient Object Category Recognition Using Classemes
* Efficient Structure from Motion by Graph Optimization
* Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces
* Element-Wise Factorization for N-View Projective Reconstruction
* Emotion Recognition from Arbitrary View Facial Images
* Energy Minimization under Constraints on Label Counts
* Enhancing Interactive Image Segmentation with Automatic Label Set Augmentation
* Error-Tolerant Image Compositing
* Estimation of 3D Object Structure, Motion and Rotation Based on 4D Affine Optical Flow Using a Multi-camera Array
* Euclidean Structure Recovery from Motion in Perspective Image Sequences via Hankel Rank Minimization
* Every Picture Tells a Story: Generating Sentences from Images
* Experimental Study of Color-Based Segmentation Algorithms Based on the Mean-Shift Concept, An
* Exploiting Loops in the Graph of Trifocal Tensors for Calibrating a Network of Cameras
* Exploiting Repetitive Object Patterns for Model Compression and Completion
* Exploring Ambiguities for Monocular Non-Rigid Shape Estimation
* Exploring the Identity Manifold: Constrained Operations in Face Space
* Extracting Structures in Image Collections for Object Recognition
* Extrinsic Camera Calibration Using Multiple Reflections
* Eye Fixation Database for Saliency Detection in Images, An
* Face Image Relighting using Locally Constrained Global Optimization
* Face Liveness Detection from a Single Image with Sparse Low Rank Bilinear Discriminative Model
* Face Recognition with Patterns of Oriented Edge Magnitudes
* Facial Contour Labeling via Congealing
* Fast and Exact Primal-Dual Iterations for Variational Problems in Computer Vision
* Fast Approximate Nearest Neighbor Methods for Non-Euclidean Manifolds with Applications to Human Activity Analysis in Videos
* Fast Covariance Computation and Dimensionality Reduction for Sub-window Features in Images
* Fast Dual Method for HIK SVM Learning, A
* Fast Dynamic Texture Detection
* Fast Multi-aspect 2D Human Detection
* Fast Multi-labelling for Stereo Matching
* Fast Optimization for Mixture Prior Models
* Feature Tracking for Wide-Baseline Image Retrieval
* Figure-Ground Image Segmentation Helps Weakly-Supervised Learning of Objects
* Finding Semantic Structures in Image Hierarchies Using Laplacian Graph Energy
* Flexible Voxels for Motion-Aware Videography
* From a Set of Shapes to Object Discovery
* Fully Isotropic Fast Marching Methods on Cartesian Grids
* Fully Isotropic Fast Marching Methods on Cartesian Grids
* Gabor Feature Based Sparse Representation for Face Recognition with Gabor Occlusion Dictionary
* Gaussian-Like Spatial Priors for Articulated Tracking
* Generalized PatchMatch Correspondence Algorithm, The
* Geodesic Shape Retrieval via Optimal Mass Transport
* Geometric Constraints for Human Detection in Aerial Imagery
* Geometric Image Parsing in Man-Made Environments
* Geometry Construction from Caustic Images
* Globally Optimal Approach for 3D Elastic Motion Estimation from Stereo Sequences, A
* Globally Optimal Multi-target Tracking on a Hexagonal Lattice
* Graph Cut Based Inference with Co-occurrence Statistics
* Guided Image Filtering
* Handling Urban Location Recognition as a 2D Homothetic Problem
* High-Quality Video Denoising Algorithm Based on Reliable Motion Estimation, A
* Hough Transform and 3D SURF for Robust Three Dimensional Classification
* Human attributes from 3D pose tracking
* Hybrid Compressive Sampling via a New Total Variation TVL1
* Image Categorization Using Directed Graphs
* Image Classification Using Super-Vector Coding of Local Image Descriptors
* Image Invariants for Smooth Reflective Surfaces
* Image Segmentation with Topic Random Field
* Image-to-Class Distance Metric Learning for Image Classification
* Improved Human Parsing with a Full Relational Model
* Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings
* Improving Local Descriptors by Embedding Global and Local Spatial Information
* Improving the Fisher Kernel for Large-Scale Image Classification
* Inferring 3D Shapes and Deformations from Single Views
* Inter-camera Association of Multi-target Tracks by On-Line Learned Appearance Affinity Models
* Intrinsic Regularity Detection in 3D Geometry
* Iterative Method with General Convex Fidelity Term for Image Restoration, An
* Joint Estimation of Motion, Structure and Geometry from Stereo Sequences
* Joint People, Event, and Location Recognition in Personal Photo Collections Using Cross-Domain Context
* Kernel Sparse Representation for Image Classification and Face Recognition
* Knowledge Based Activity Recognition with Dynamic Bayesian Network
* LACBoost and FisherBoost: Optimally Building Cascade Classifiers
* Learning a Fine Vocabulary
* Learning Artistic Lighting Template from Portrait Photographs
* Learning PDEs for Image Restoration via Optimal Control
* Learning Pre-attentive Driving Behaviour from Holistic Visual Features
* Learning Relations among Movie Characters: A Social Network Perspective
* Learning Shape Detector by Quantizing Curve Segments with Multiple Distance Metrics
* Learning Shape Segmentation Using Constrained Spectral Clustering and Probabilistic Label Transfer
* Learning to Detect Roads in High-Resolution Aerial Images
* Learning to Recognize Objects from Unseen Modalities
* Learning What and How of Contextual Models for Scene Labeling
* Lighting and Pose Robust Face Sketch Synthesis
* Lighting Aware Preprocessing for Face Recognition across Varying Illumination
* Local Bag-of-Features Model for Large-Scale Object Retrieval, A
* Local Occlusion Detection under Deformations Using Topological Invariants
* Localizing Objects While Learning Their Appearance
* Location Recognition Using Prioritized Feature Matching
* Loosely Distinctive Features for Robust Surface Alignment
* Making Action Recognition Robust to Occlusions and Viewpoint Changes
* Manifold Learning for Object Tracking with Multiple Motion Dynamics
* Manifold Valued Statistics, Exact Principal Geodesic Analysis and the Effect of Linear Approximations
* Max-Margin Dictionary Learning for Multiclass Image Categorization
* Maximum Margin Distance Learning for Dynamic Texture Recognition
* Membrane Nonrigid Image Registration
* Memory-Based Particle Filter for Tracking Objects with Large Variation in Pose and Appearance
* MIForests: Multiple-Instance Learning with Randomized Trees
* Minimal Case Solution to the Calibrated Relative Pose Problem for the Case of Two Known Orientation Angles, A
* Model of Volumetric Shape for the Analysis of Longitudinal Alzheimer's Disease Data, A
* Modeling and Analysis of Dynamic Behaviors of Web Image Collections
* Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification
* Modeling the Temporal Extent of Actions
* Monocular 3D Scene Modeling and Inference: Understanding Multi-Object Traffic Scenes
* Motion Profiles for Deception Detection Using Visual Cues
* MRF Inference by k-Fan Decomposition and Tight Lagrangian Relaxation
* Multi-class Classification on Riemannian Manifolds for Video Surveillance
* Multi-label Feature Transform for Image Classifications
* Multi-label Linear Discriminant Analysis
* Multi-Person Tracking with Sparse Detection and Continuous Segmentation
* Multi-stage Sampling with Boosting Cascades for Pedestrian Detection in Images and Videos
* Multiple Hypothesis Video Segmentation from Superpixel Flows
* Multiple Instance Metric Learning from Automatically Labeled Bags of Faces
* Multiple Target Tracking in World Coordinate with Single, Minimally Calibrated Camera
* Multiresolution Models for Object Detection
* New Algorithmic Approach for Contrast Enhancement, A
* NF-Features: No-Feature-Features for Representing Non-textured Regions
* Non-local Characterization of Scenery Images: Statistics, 3D Reasoning, and a Generative Model
* Non-Local Kernel Regression for Image and Video Restoration
* Nonlocal Multiscale Hierarchical Decomposition on Graphs
* Novel Parameter Estimation Algorithm for the Multivariate t-Distribution and Its Application to Computer Vision, A
* Object Classification Using Heterogeneous Co-Occurrence Features
* Object Classification Using Heterogeneous Co-Occurrence Features
* Object of Interest Detection by Saliency Learning
* Object Recognition Using Junctions
* Object Recognition with Hierarchical Stel Models
* Object Segmentation by Long Term Analysis of Point Trajectories
* Object, Scene and Actions: Combining Multiple Features for Human Action Recognition
* Occlusion Boundary Detection Using Pseudo-depth
* On Parameter Learning in CRF-Based Approaches to Object Class Image Segmentation
* One-Shot Optimal Exposure Control
* Optimal Contour Closure by Superpixel Grouping
* Optimizing Complex Loss Functions in Structured Prediction
* Optimum Subspace Learning and Error Correction for Tensors
* Oriented Flux Symmetry Based Active Contour Model for Three Dimensional Vessel Segmentation, An
* P2-pi: A Minimal Solution for Registration of 3D Points to 3D Planes
* Part-Based Feature Synthesis for Human Detection
* Partition Min-Hash for Partial Duplicate Image Discovery
* Perspective Imaging under Structured Light
* Photo-Consistent Planar Patches from Unstructured Cloud of Points
* Photometric Stereo for Dynamic Surface Orientations
* Photometric Stereo from Maximum Feasible Lambertian Reflections
* Piecewise Quadratic Reconstruction of Non-Rigid Surfaces from Monocular Sequences
* Practical Autocalibration
* Practical Methods for Convex Multi-View Reconstruction
* Predicting Facial Beauty without Landmarks
* Probabilistic Deformable Surface Tracking from Multiple Videos
* Programmable Aperture Camera Using LCoS
* Quadratic-Chi Histogram Distance Family, The
* Randomized Locality Sensitive Vocabularies for Bag-of-Features Model
* Real-Time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid
* Real-Time Specular Highlight Removal Using Bilateral Filtering
* Real-Time Spherical Mosaicing Using Whole Image Alignment
* Recognizing Partially Occluded Faces from a Single Sample Per Class Using String-Based Matching
* Recursive Coarse-to-Fine Localization for Fast Object Detection
* Representing Pairwise Spatial and Temporal Relations for Action Recognition
* Resampling Structure from Motion
* Reweighted Random Walks for Graph Matching
* Ring-Light Photometric Stereo
* Robust and Fast Collaborative Tracking with Two Stage Sparse Optimization
* Robust and Scalable Approach to Face Identification, A
* Robust Face Recognition Using Probabilistic Facial Trait Code
* Robust Fusion: Extreme Value Theory for Recognition Score Normalization
* Robust Head Pose Estimation Using Supervised Manifold Learning
* Robust Multi-View Boosting with Priors
* Rotation Invariant Non-rigid Shape Matching in Cluttered Scenes
* Scene Carving: Scene Consistent Image Retargeting
* Seeing People in Social Context: Recognizing People and Social Relationships
* Seeing through Obscure Glass
* Segmenting Salient Objects from Images and Videos
* Self-Adapting Feature Layers
* Semantic Label Sharing for Learning with Many Categories
* Semantic Segmentation of Urban Scenes Using Dense Depth Maps
* Semi-explicit Shape Model for Multi-object Detection and Classification, The
* Sequential Non-Rigid Structure-from-Motion with the 3D-Implicit Low-Rank Shape Model
* Shape Analysis of Planar Objects with Arbitrary Topologies Using Conformal Geometry
* Shape from Second-Bounce of Light Transport
* Shrinkage Learning Approach for Single Image Super-Resolution with Overcomplete Representations, A
* Simultaneous Segmentation and Figure/Ground Organization Using Angular Embedding
* Single Image Deblurring Using Motion Density Functions
* Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters
* Sparse Non-linear Least Squares Optimization for Geometric Vision
* Spatial Statistics of Visual Keypoints for Texture Recognition
* Spatial-Temporal Granularity-Tunable Gradients Partition (STGGP) Descriptors for Human Detection
* Spatially-Sensitive Affine-Invariant Image Descriptors
* Spherical Harmonics Shape Model for Level Set Segmentation, A
* Stacked Hierarchical Labeling
* State Estimation in a Document Image and Its Application in Text Block Identification and Text Line Extraction
* Static SMC Sampler on Shapes for the Automated Segmentation of Aortic Calcifications, A
* Stochastic Graph Evolution Framework for Robust Multi-target Tracking, A
* Streakline Representation of Flow in Crowded Scenes, A
* Structural Filter Approach to Human Detection, A
* Structured Output Ordinal Regression for Dynamic Facial Emotion Intensity Prediction
* SuperParsing: Scalable Nonparametric Image Parsing with Superpixels
* Superpixels and Supervoxels in an Energy Optimization Framework
* Supervised and Unsupervised Clustering with Probabilistic Shift
* Supervised Label Transfer for Semantic Segmentation of Street Scenes
* Tensor Sparse Coding for Region Covariances
* Texture Regimes for Entropy-Based Multiscale Image Analysis
* Theory of Optimal View Interpolation with Depth Inaccuracy
* Thinking Inside the Box: Using Appearance Models and Context Based on Room Geometry
* Towards Computational Models of the Visual Aesthetic Appeal of Consumer Videos
* Towards More Efficient and Effective LP-Based Algorithms for MRF Optimization
* Towards Optimal Naive Bayes Nearest Neighbor
* Tracklet Descriptors for Action Modeling and Video Analysis
* TriangleFlow: Optical Flow with Triangulation-Based Higher-Order Likelihoods
* Two-Phase Kernel Estimation for Robust Motion Deblurring
* Unified Contour-Pixel Model for Figure-Ground Segmentation, A
* Unique Signatures of Histograms for Local Surface Description
* Unsupervised Learning of Functional Categories in Video Scenes
* Using Partial Edge Contour Matches for Efficient Object Category Localization
* Velocity-Dependent Shutter Sequences for Motion Deblurring
* Video Synchronization Using Temporal Signals from Epipolar Lines
* View and Style-Independent Action Manifolds for Human Activity Recognition
* Visibility Subspaces: Uncalibrated Photometric Stereo with Shadows
* Visual Recognition with Humans in the Loop
* Visual Tracking Using a Pixelwise Spatiotemporal Oriented Energy Representation
* Voting by Grouping Dependent Parts
* We Are Family: Joint Pose Estimation of Multiple Persons
* Weakly Supervised Classification of Objects in Images Using Soft Random Forests
* Weakly Supervised Shape Based Object Detection with Particle Filter
* Weakly-Paired Maximum Covariance Analysis for Multimodal Dimensionality Reduction and Transfer Learning
* What Does Classifying More Than 10,000 Image Categories Tell Us?
* What Is the Chance of Happening: A New Way to Predict Where People Look
* What, Where and How Many? Combining Object Detectors and CRFs
* Why Did the Person Cross the Road (There)? Scene Understanding Using Probabilistic Logic Models and Common Sense Reasoning
* Word Spotting in the Wild
329 for ECCV10

ECCV12 * *ECCV
* 3D Reconstruction of Dynamic Scenes with Multiple Handheld Cameras
* 3D2PM: 3D Deformable Part Models
* Abnormal Object Detection by Canonical Scene-Based Contextual Model
* Accelerated Large Scale Optimization by Concomitant Hashing
* Action Recognition Using Subtensor Constraint
* Action Recognition with Exemplar Based 2.5D Graph Matching
* Active Frame Selection for Label Propagation in Videos
* Activity Forecasting
* Age Invariant Face Verification with Relative Craniofacial Growth Model
* Analyzing the Subspace Structure of Related Images: Concurrent Segmentation of Image Sets
* Annotation Propagation in Large Image Databases via Dense Image Correspondence
* Approximate Gaussian Mixtures for Large Scale Vocabularies
* Approximate MRF Inference Using Bounded Treewidth Subgraphs
* Are You Really Smiling at Me? Spontaneous versus Posed Enjoyment Smiles
* Artistic Image Classification: An Analysis on the PRINTART Database
* Attribute Discovery via Predictable Discriminative Binary Codes
* Attribute Learning for Understanding Unstructured Social Activity
* Attributes for Classifier Feedback
* Augmented Attribute Representations
* Auto-Grouped Sparse Representation for Visual Analysis
* Automatic Exposure Correction of Consumer Photographs
* Automatic Localization of Balloon Markers and Guidewire in Rotational Fluoroscopy with Application to 3D Stent Reconstruction
* Automatic Segmentation of Unknown Objects, with Application to Baggage Security
* Automatic Tracking of a Large Number of Moving Targets in 3D
* Background Inpainting for Videos with Dynamic Objects and a Free-Moving Camera
* Background Subtraction Using Low Rank and Group Sparsity Constraints
* Background Subtraction with Dirichlet Processes
* Bayesian Approach to Alignment-Based Image Hallucination, A
* Bayesian Blind Deconvolution with General Sparse Image Priors
* Bayesian Face Revisited: A Joint Formulation
* Beyond Bounding-Boxes: Learning Object Shape by Model-Driven Grouping
* Beyond Feature Points: Structured Prediction for Monocular Non-rigid 3D Reconstruction
* Beyond Spatial Pyramids: A New Feature Extraction Framework with Dense Spatial Sampling for Image Classification
* Beyond the Line of Sight: Labeling the Underlying Surfaces
* Blind Correction of Optical Aberrations
* Block-Sparse RPCA for Consistent Foreground Detection
* Blur-Kernel Estimation from Spectral Irregularities
* Bottom-Up Perceptual Organization of Images into Object Part Hypotheses
* Camera Pose Estimation Using First-Order Curve Differential Geometry
* Categorizing Turn-Taking Interactions
* Clustering by Composition: Unsupervised Discovery of Image Categories
* Co-inference for Multi-modal Scene Analysis
* Coherent Filtering: Detecting Coherent Motions from Crowd Clutters
* Color Constancy, Intrinsic Images, and Shape Estimation
* Combining Per-frame and Per-track Cues for Multi-person Action Recognition
* Comparative Evaluation of Binary Features
* Comparison of the Statistical Properties of IQA Databases Relative to a Set of Newly Captured High-Definition Images, A
* Complex Events Detection Using Data-Driven Concepts
* Connecting Missing Links: Object Discovery from Sparse Observations Using 5 Million Product Images
* Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes
* Context-Based Automatic Local Image Enhancement
* Contextual Object Detection Using Set-Based Classification
* Continuous Markov Random Fields for Robust Stereo Estimation
* Continuous Regression for Non-rigid Image Alignment
* Contraction Moves for Geometric Model Fitting
* Convex Discrete-Continuous Approach for Markov Random Fields, A
* Convolutional Treelets Binary Feature Approach to Fast Keypoint Recognition, A
* Coregistration: Simultaneous Alignment and Modeling of Articulated 3D Shape
* Cost-Sensitive Top-Down/Bottom-Up Inference for Multiscale Activity Recognition
* Covariance Propagation and Next Best View Planning for 3D Reconstruction
* Crosstalk Cascades for Frame-Rate Pedestrian Detection
* Dating Historical Color Images
* Deconvolving PSFs for a Better Motion Deblurring Using Multiple Images
* Depth and Deblurring from a Spectrally-Varying Depth-of-Field
* Depth Extraction from Video Using Non-parametric Sampling
* Depth Matters: Influence of Depth Cues on Visual Saliency
* Depth Recovery Using an Adaptive Color-Guided Auto-Regressive Model
* Describing Clothing by Semantic Attributes
* Descriptor Learning Using Convex Optimisation
* Detecting Actions, Poses, and Objects with Relational Phraselets
* Detecting and Reconstructing 3D Mirror Symmetric Objects
* Detection of Independently Moving Objects in Non-planar Scenes via Multi-Frame Monocular Epipolar Constraint
* Diagnosing Error in Object Detectors
* Dictionary Learning Approach for Classification: Separating the Particularity and the Commonality, A
* Dictionary-Based Face Recognition from Video
* Dilated Divergence Based Scale-Space Representation for Curve Analysis
* Directional Space-Time Oriented Gradients for 3D Visual Pattern Analysis
* Discovering Latent Domains for Multisource Domain Adaptation
* Discrete Chain Graph Model for 3d+t Cell Tracking with High Misdetection Robustness, A
* Discriminative Bayesian Active Shape Models
* Discriminative Data-Dependent Mixture-Model Approach for Multiple Instance Learning in Image Classification, A
* Discriminative Decorrelation for Clustering and Classification
* Disentangling Factors of Variation for Facial Expression Recognition
* Displacement Template with Divide-and-Conquer Algorithm for Significantly Improving Descriptor Based Face Recognition Approaches
* Divergence-Free Motion Estimation
* Diverse M-Best Solutions in Markov Random Fields
* Dog Breed Classification Using Part Localization
* Domain Adaptive Dictionary Learning
* Dual-Force Metric Learning for Robust Distracter-Resistant Tracker
* Dynamic Context for Tracking behind Occlusions
* Dynamic Eye Movement Datasets and Learnt Saliency Models for Visual Action Recognition
* Dynamic Facial Expression Recognition Using Longitudinal Facial Expression Atlases
* Dynamic Probabilistic CCA for Analysis of Affective Behaviour
* Dynamic Programming for Approximate Expansion Algorithm
* Effective Use of Frequent Itemset Mining for Image Classification
* Efficient Articulated Trajectory Reconstruction Using Dynamic Programming and Filters
* Efficient Closed-Form Solution to Generalized Boundary Detection
* Efficient Discriminative Projections for Compact Binary Descriptors
* Efficient Exact Inference for 3D Indoor Scene Understanding
* Efficient Misalignment-Robust Representation for Real-Time Face Recognition
* Efficient Monte Carlo Sampler for Detecting Parametric Objects in Large Scenes
* Efficient Nonlocal Regularization for Optical Flow
* Efficient Optimization for Low-Rank Integrated Bilinear Classifiers
* Efficient Point-to-Subspace Query in L_1 with Application to Robust Face Recognition
* Efficient Recursive Algorithms for Computing the Mean Diffusion Tensor and Applications to DTI Segmentation
* Efficient Similarity Derived from Kernel-Based Transition Probability
* Elastic Shape Matching of Parameterized Surfaces Using Square Root Normal Fields
* Elevation Angle from Reflectance Monotonicity: Photometric Stereo for General Isotropic Reflectances
* Ensemble Partitioning for Unsupervised Image Categorization
* Estimation of Intrinsic Image Sequences from Image+Depth Video
* Evaluation of Image Segmentation Quality by Adaptive Ground Truth Composition
* Exact Acceleration of Linear Object Detectors
* Exploiting Sparse Representations for Robust Analysis of Noisy Complex Video Scenes
* Exploiting the Circulant Structure of Tracking-by-Detection with Kernels
* Exploring the Spatial Hierarchy of Mixture Models for Human Pose Estimation
* Exposure Stacks of Live Scenes with Hand-Held Cameras
* Extracting 3D Scene-Consistent Object Proposals and Depth from Stereo Images
* Face Association across Unconstrained Video Frames Using Conditional Random Fields
* Facial Action Transfer with Personalized Bilinear Regression
* Fast Approximations to Structured Sparse Coding and Applications to Object Classification
* Fast Fusion Moves for Multi-Model Estimation
* Fast Illumination and Deformation Insensitive Image Comparison Algorithm Using Wavelet-Based Geodesics, A
* Fast Parameter Sensitivity Analysis of PDE-Based Image Processing Methods
* Fast Planar Correlation Clustering for Image Segmentation
* Fast Regularization of Matrix-Valued Images
* Fast Tiered Labeling with Topological Priors
* Filter-Based Mean-Field Inference for Random Fields with Higher-Order Terms and Product Label-Spaces
* Finding Correspondence from Multiple Images via Sparse and Low-Rank Decomposition
* Finding People Using Scale, Rotation and Articulation Invariant Matching
* Finding the Exact Rotation between Two Images Independently of the Translation
* Fourier Kernel Learning
* Free Hand-Drawn Sketch Segmentation
* Frequency Analysis of Transient Light Transport with Applications in Bare Sensor Imaging
* Frequency-Space Decomposition and Acquisition of Light Transport under Spatially Varying Illumination
* From Meaningful Contours to Discriminative Object Shape
* Full Body Performance Capture under Uncontrolled and Varying Illumination: A Shading-Based Approach
* Gait Recognition by Ranking
* General and Nested Wiberg Minimization: L2 and Maximum Likelihood
* Generalized Roof Duality for Multi-Label Optimization: Optimal Lower Bounds and Persistency
* Generative Model for Online Depth Fusion, A
* Generative Model for Simultaneous Estimation of Human Body Shape and Pixel-Level Segmentation, A
* Generic Cuts: An Efficient Algorithm for Optimal Inference in Higher Order MRF-MAP
* Geodesic Saliency Using Background Priors
* Global Hypotheses Verification Method for 3D Object Recognition, A
* Global Optimization of Object Pose and Motion from a Single Rolling Shutter Image with Automatic 2D-3D Matching
* Globally Optimal Closed-Surface Segmentation for Connectomics
* GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs
* Going with the Flow: Pedestrian Efficiency in Crowded Scenes
* Good Regions to Deblur
* Grain Segmentation of 3D Superalloy Images Using Multichannel EWCVT under Human Annotation Constraints
* Graph Degree Linkage: Agglomerative Clustering on a Directed Graph
* Graph Matching via Sequential Monte Carlo
* Group Tracking: Exploring Mutual Relations for Multiple Object Tracking
* Guaranteed Ellipse Fitting with the Sampson Distance
* Hand Pose Estimation and Hand Shape Classification Using Multi-layered Randomized Decision Forests
* Has My Algorithm Succeeded? An Evaluator for Human Pose Estimators
* Hausdorff Distance Constraint for Multi-surface Segmentation
* Heliometric Stereo: Shape from Sun Position
* Hough Regions for Joining Instance Localization and Segmentation
* Human Activities as Stochastic Kronecker Graphs
* Hybrid Classifiers for Object Classification with a Rich Background
* Image Annotation Using Metric Learning in Semantic Neighbourhoods
* Image Enhancement Using Calibrated Lens Simulations
* Image Guided Tone Mapping with Locally Nonlinear Model
* Image Labeling on a Network: Using Social-Network Metadata for Image Classification
* Image Retrieval with Structured Object Queries Using Latent Ranking SVM
* Improved Reconstruction of Deforming Surfaces by Cancelling Ambient Occlusion
* Improving Image-Based Localization by Active Correspondence Search
* Improving NCC-Based Direct Visual Tracking
* In Defence of Negative Mining for Annotating Weakly Labelled Data
* In Defence of RANSAC for Outlier Rejection in Deformable Registration
* Indoor Segmentation and Support Inference from RGBD Images
* Inferring Gene Interaction Networks from ISH Images via Kernelized Graphical Models
* Information Theoretic Learning for Pixel-Based Visual Agents
* Interactive Facial Feature Localization
* Inverse Rendering of Faces on a Cloudy Day
* Jet-Based Local Image Descriptors
* Joint Classification-Regression Forests for Spatially Structured Multi-Object Segmentation
* Joint Face Alignment with Non-parametric Shape Models
* Joint Face Alignment: Rescue Bad Alignments with Good Ones by Regularized Re-fitting
* Joint Image and Word Sense Discrimination for Image Retrieval
* KAZE Features
* Kernelized Temporal Cut for Online Temporal Segmentation and Recognition
* Labeling Images by Integrating Sparse Multiple Distance Learning and Semantic Context Modeling
* Laplacian Meshes for Monocular 3D Shape Recovery
* Large Scale Visual Geo-Localization of Images in Mountainous Terrain
* Large-Lexicon Attribute-Consistent Text Recognition in Natural Images
* Large-Scale Gaussian Process Classification with Flexible Adaptive Histogram Kernels
* Latent Hough Transform for Object Detection
* Latent Pyramidal Regions for Recognizing Scenes
* Lazy Flipper: Efficient Depth-Limited Exhaustive Search in Discrete Graphical Models, The
* Leafsnap: A Computer Vision System for Automatic Plant Species Identification
* Learning Class-to-Image Distance via Large Margin and L1-Norm Regularization
* Learning Deformations with Parallel Transport
* Learning Discriminative Spatial Relations for Detector Dictionaries: An Application to Pedestrian Detection
* Learning Domain Knowledge for Façade Labelling
* Learning Human Interaction by Interactive Phrases
* Learning Hybrid Part Filters for Scene Recognition
* Learning Spatially-Smooth Mappings in Non-Rigid Structure From Motion
* Learning to Efficiently Detect Repeatable Interest Points in Depth Data
* Learning to Match Appearances by Correlations in a Covariance Metric Space
* Learning to Recognize Daily Actions Using Gaze
* Learning to Recognize Unsuccessful Activities Using a Two-Layer Latent Structural Model
* Learning to Segment a Video to Clips Based on Scene and Camera Motion
* Learning-Based Symmetry Detection in Natural Images
* Lie Bodies: A Manifold Representation of 3D Human Shape
* Local Expert Forest of Score Fusion for Video Event Classification
* Local Higher-Order Statistics (LHS) for Texture Categorization and Facial Analysis
* Local Label Descriptor for Example Based Semantic Image Labeling
* Local Log-Euclidean Covariance Matrix (L2ECM) for Image Representation and Its Applications
* Locally Linear Regression Model for Boundary Preserving Regularization in Stereo Matching, A
* Long-Range Spatio-Temporal Modeling of Video with Application to Fire Detection
* Loss-Specific Training of Non-Parametric Image Restoration Models: A New State of the Art
* Low-Rank Sparse Learning for Robust Visual Tracking
* Manifold Statistics for Essential Matrices
* Match Graph Construction for Large Image Databases
* MatchMiner: Efficient Spanning Structure Mining in Large Image Collections
* Measuring Image Distances via Embedding in a Semantic Manifold
* Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost
* Min-Space Integral Histogram
* Minimal Correlation Classification
* Minimal Solution for Camera Calibration Using Independent Pairwise Correspondences, A
* Mixed-Resolution Patch-Matching
* Mixture Component Identification and Learning for Visual Recognition
* Mobile Product Image Search by Automatic Query Object Extraction
* Modeling Complex Temporal Composition of Actionlets for Activity Prediction
* Monocular Object Detection Using 3D Geometric Primitives
* Morphable Displacement Field Based Image Matching for Face Recognition across Pose
* Motion Capture of Hands in Action Using Discriminative Salient Points
* Motion Interchange Patterns for Action Recognition in Unconstrained Videos
* Motion-Aware Structured Light Using Spatio-Temporal Decodable Patterns
* Moving Object Segmentation Using Motor Signals
* MP)2T: Multiple People Multiple Parts Tracker
* Multi-channel Shape-Flow Kernel Descriptors for Robust Video Event Detection and Retrieval
* Multi-component Models for Object Detection
* Multi-scale Clustering of Frame-to-Frame Correspondences for Motion Segmentation
* Multi-Scale Patch Based Collaborative Representation for Face Recognition with Margin Distribution Optimization
* Multidimensional Spectral Hashing
* Multiple View Object Cosegmentation Using Appearance and Stereo Cues
* N-tuple Color Segmentation for Multi-View Silhouette Extraction
* Naturalistic Open Source Movie for Optical Flow Evaluation, A
* Negative Evidences and Co-occurences in Image Retrieval: The Benefit of PCA and Whitening
* Nested Pictorial Structures
* Nested Sparse Quantization for Efficient Feature Coding
* New Biologically Inspired Color Image Descriptor, A
* New Set of Quartic Trivariate Polynomial Equations for Stratified Camera Self-calibration under Zero-Skew and Constant Parameters Assumptions, A
* No Bias Left behind: Covariate Shift Adaptation for Discriminative 3D Pose Estimation
* Non-causal Temporal Prior for Video Deblocking
* Non-parametric Hierarchical Model to Discover Behavior Dynamics from Tracks, A
* Non-rigid Shape Registration: A Single Linear Least Squares Framework
* Nonmetric Priors for Continuous Multilabel Optimization
* Nonuniform Lattice Regression for Modeling the Camera Imaging Pipeline
* Novel Fast Method for L-inf Problems in Multiview Geometry, A
* Novel Material-Aware Feature Descriptor for Volumetric Image Registration in Diffusion Tensor Space, A
* Numerically Stable Optimization of Polynomial Solvers for Minimal Problems
* Object Co-detection
* Object Detection Using Strongly-Supervised Deformable Part Models
* Object-Centric Spatial Pooling for Image Classification
* On Learning Higher-Order Consistency Potentials for Multi-class Pixel Labeling
* On Tensor-Based PDEs and Their Corresponding Variational Formulations with Application to Color Image Denoising
* On the Convergence of Graph Matching: Graduated Assignment Revisited
* On the Statistical Determination of Optimal Camera Configurations in Large Scale Surveillance Networks
* Online Learned Discriminative Part-Based Appearance Models for Multi-human Tracking
* Online Learning of Linear Predictors for Real-Time Tracking
* Online Moving Camera Background Subtraction
* Online Spatio-temporal Structural Context Learning for Visual Tracking
* Online Video Segmentation by Bayesian Split-Merge Clustering
* Optimal Templates for Nonrigid Surface Reconstruction
* Order-Preserving Sparse Coding for Sequence Classification
* Pairwise Rotation Invariant Co-Occurrence Local Binary Pattern [Conf]
* Parameterless Line Segment and Elliptical Arc Detector with Enhanced Ellipse Fitting, A
* Parametric Manifold of an Object under Different Viewing Directions
* Particle Filter Framework for Contour Detection, A
* Patch Based Synthesis for Single Depth Image Super-Resolution
* Patch Complexity, Finite Pixel Correlations and Optimal Denoising
* PatchMatchGraph: Building a Graph of Dense Patch Correspondences for Label Transfer
* People Orientation Recognition by Mixtures of Wrapped Distributions on Random Trees
* People Watching: Human Actions as a Cue for Single View Geometry
* Per-patch Descriptor Selection Using Surface and Scene Properties
* Performance Capture of Interacting Characters with Handheld Kinects
* Photo Sequencing
* Point of Gaze Estimation through Corneal Surface Reflection in an Active Illumination Environment
* Polynomial Regression on Riemannian Manifolds
* Pose Invariant Approach for Face Recognition at Distance
* Probabilistic Approach to Robust Matrix Factorization, A
* Probabilistic Derivative Measure Based on the Distribution of Intensity Difference, A
* Propagative Hough Voting for Human Activity Recognition
* QCQP Approach to Triangulation, A
* Quaternion-Based Spectral Saliency Detection for Eye Fixation Prediction
* Query Specific Fusion for Image Retrieval
* Rainbow Flash Camera: Depth Edge Extraction Using Complementary Colors
* Random Forest for Image Annotation
* Randomized Spatial Partition for Scene Recognition
* Reading Ancient Coins: Automatically Identifying Denarii Using Obverse Legend Seeded Retrieval
* Real-Time Camera Tracking: When is High Frame-Rate Best?
* Real-Time Compressive Tracking
* Real-Time Human Pose Tracking from Range Data
* Recognizing Complex Events Using Large Margin Joint Low-Level Event Model
* Recognizing Materials from Virtual Examples
* Reconstructing 3D Human Pose from 2D Image Landmarks
* Reconstructing the World's Museums
* Recording and Playback of Camera Shake: Benchmarking Blind Deconvolution with a Real-World Database
* Recursive Bilateral Filtering
* Reduced Analytical Dependency Modeling for Classifier Fusion
* Reflectance and Natural Illumination from a Single Image
* Refractive Calibration of Underwater Cameras
* Relaxed Pairwise Learned Metric for Person Re-identification
* Renormalization Returns: Hyper-renormalization and Its Applications
* Repairing Sparse Low-Rank Texture
* Road Scene Segmentation from a Single Image
* Robust 3D Action Recognition with Random Occupancy Patterns
* Robust and Accurate Shape Model Fitting Using Random Forest Regression Voting
* Robust and Efficient Doubly Regularized Metric Learning Approach, A
* Robust and Efficient Subspace Segmentation via Least Squares Regression
* Robust and Practical Face Recognition via Structured Sparsity
* Robust Fitting for Multiple View Geometry
* Robust Point Matching Revisited: A Concave Optimization Approach
* Robust Regression
* Robust Tracking with Weighted Online Structured Learning
* Saliency Modeling from Image Histograms
* Salient Object Detection: A Benchmark
* Scale Invariant Optical Flow
* Scale of Geometric Texture, The
* Scale Robust Multi View Stereo
* Scene Aligned Pooling for Complex Video Recognition
* Scene Recognition on the Semantic Manifold
* Scene Semantics from Long-Term Observation of People
* Script Data for Attribute-Based Recognition of Composite Activities
* Seam Segment Carving: Retargeting Images to Irregularly-Shaped Image Domains
* SEEDS: Superpixels Extracted Via Energy-Driven Sampling
* Segmentation Based Particle Filtering for Real-Time 2D Object Tracking
* Segmentation over Detection by Coupled Global and Local Sparse Representations
* Segmentation Propagation in ImageNet
* Segmentation with Non-linear Regional Constraints via Line-Search Cuts
* Self-similar Sketch
* Semantic Segmentation with Second-Order Pooling
* Semi-intrinsic Mean Shift on Riemannian Manifolds
* Semi-Nonnegative Matrix Factorization for Motion Segmentation with Missing Data
* Separability Oriented Preprocessing for Illumination-Insensitive Face Recognition
* Sequential Spectral Learning to Hash with Multiple Representations
* Set Based Discriminative Ranking for Recognition
* Shape and Reflectance from Natural Illumination
* Shape from Angle Regularity
* Shape from Fluorescence
* Shape from Single Scattering for Translucent Objects
* Shape Sharing for Object Segmentation
* Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation
* Similarity Constrained Latent Support Vector Machine: An Application to Weakly Supervised Action Classification
* Simultaneous Compaction and Factorization of Sparse Image Motion Matrices
* Simultaneous Image Classification and Annotation via Biased Random Walk on Tri-relational Graph
* Simultaneous Shape and Pose Adaption of Articulated Models Using Linear Optimization
* Size Matters: Exhaustive Geometric Verification for Image Retrieval
* Soft Inextensibility Constraints for Template-Free Non-rigid Reconstruction
* Space-Variant Descriptor Sampling for Action Recognition Based on Saliency and Eye Movements
* Sparse Coding and Dictionary Learning for Symmetric Positive Definite Matrices: A Kernel Approach
* Sparse Embedding: A Framework for Sparsity Promoting Dimensionality Reduction
* Sparselet Models for Efficient Multiclass Object Detection
* Spatial and Angular Variational Super-Resolution of 4D Light Fields
* Spatio-Temporal Phrases for Activity Recognition
* Spatiotemporal Descriptor for Wide-Baseline Stereo Reconstruction of Non-rigid and Ambiguous Scenes
* Spectral Demons: Image Registration via Global Spectral Correspondence
* Spring Lattice Counting Grids: Scene Recognition Using Deformable Positional Constraints
* Statistical Inference of Motion in the Invisible
* Statistics of Patch Offsets for Image Completion
* Stixels Motion Estimation without Optical Flow Computation
* Streaming Hierarchical Video Segmentation
* Structured Image Segmentation Using Kernelized Features
* Subspace Learning in Krein Spaces: Complete Kernel Fisher Discriminant Analysis with Indefinite Kernels
* Super-Resolution-Based Inpainting
* Supervised Assessment of Segmentation Hierarchies
* Supervised Earth Mover's Distance Learning and Its Computer Vision Applications
* Supervised Geodesic Propagation for Semantic Label Transfer
* Taking Mobile Multi-object Tracking to the Next Level: People, Unknown Objects, and Carried Items
* Taxonomic Multi-class Prediction and Person Layout Using Efficient Structured Ranking
* Team Activity Recognition in Sports
* Tensor Voting Approach for Multi-View 3D Scene Flow Estimation and Refinement, A
* Text Image Deblurring Using Text-Specific Properties
* Theoretical Analysis of Camera Response Functions in Image Deblurring, A
* Three-Layered Approach to Facade Parsing, A
* To Track or To Detect? An Ensemble Framework for Optimal Selection
* Towards Optimal Design of Time and Color Multiplexing Codes
* Towards Optimal Non-rigid Surface Tracking
* Tracking Feature Points in Uncalibrated Images with Radial Distortion
* Tracking Using Motion Patterns for Very Crowded Scenes
* Trajectory-Based Modeling of Human Actions with Motion Reference Points
* TreeCANN: k-d Tree Coherence Approximate Nearest Neighbor Algorithm
* TriCoS: A Tri-level Class-Discriminative Co-segmentation Method for Image Classification
* Two-Granularity Tracking: Mediating Trajectory and Detection Graphs for Tracking under Occlusions
* Two-View Underwater Structure and Motion for Cameras under Flat Refractive Interfaces
* Undoing the Damage of Dataset Bias
* Unified Framework for Multi-target Tracking and Collective Activity Recognition, A
* Unified View on Deformable Shape Factorizations, A
* Unifying Theory of Active Discovery and Learning, A
* Unsupervised and Supervised Visual Codes with Restricted Boltzmann Machines
* Unsupervised Discovery of Mid-Level Discriminative Patches
* Unsupervised Temporal Commonality Discovery
* Using Linking Features in Learning Non-parametric Part Models
* V1-Inspired Features Induce a Weighted Margin in SVMs
* Video Matting Using Multi-frame Nonlocal Matting Laplacian
* View-Invariant Action Recognition Using Latent Kernelized Structural SVM
* Visibility Probability Structure from SfM Datasets and Applications
* Visual Dictionary Learning for Joint Object Categorization and Segmentation
* Visual Recognition Using Local Quantized Patterns
* Visual Tracking via Adaptive Tracker Selection with Multiple Features
* WaSH: Weighted alpha-Shapes for Local Feature Detection
* What Makes a Good Detector?: Structured Priors for Learning from Few Examples
* Worldwide Pose Estimation Using 3D Point Clouds
408 for ECCV12

ECCV14 * *ECCV
* 30Hz Object Detection with DPM V5
* 3D Interest Point Detection via Discriminative Learning
* 3D Jigsaw Puzzle: Mapping Large Indoor Spaces, The
* 3D Reconstruction of Dynamic Textures in Crowd Sourced Data
* Accurate Intrinsic Calibration of Depth Camera with Cuboids
* Action Recognition Using Super Sparse Coding Vector with Spatio-temporal Awareness
* Action Recognition with Stacked Fisher Vectors
* Action-Reaction: Forecasting the Dynamics of Human Interaction
* Active Deformable Part Models Inference
* Active Patch Model for Real World Texture and Appearance Classification, An
* Active Random Forests: An Application to Autonomous Unfolding of Clothes
* Activity Group Localization by Modeling the Relations among Participants
* Affine Subspace Representation for Feature Description
* All-In-Focus Synthetic Aperture Imaging
* Alpha Matting of Motion-Blurred Objects in Bracket Sequence Images
* Analysis of Errors in Graph-Based Keypoint Matching and Proposed Solutions, An
* Analyzing the Performance of Multilayer Neural Networks for Object Recognition
* Appearances Can Be Deceiving: Learning Visual Tracking from Few Trajectory Annotations
* Architectural Style Classification Using Multinomial Latent Logistic Regression
* As-Rigid-As-Possible Stereo under Second Order Smoothness Priors
* Assessing the Quality of Actions
* Attributes Make Sense on Segmented Objects
* Automatic Single-View Calibration and Rectification from Parallel Planar Curves
* Bayesian Nonparametric Intrinsic Image Decomposition
* Bilateral Functions for Global Motion Modeling
* Binary Codes Embedding for Fast Image Tagging with Incomplete Labels
* Blind Deblurring Using Internal Patch Recurrence
* Boosting VLAD with Supervised Dictionary Learning and High-Order Statistics
* C Clustering with Hypergraphs: The Case for Large Hyperedges
* Canonical Correlation Analysis on Riemannian Manifolds and Its Applications
* Category-Specific Video Summarization
* Change Detection in the Presence of Motion Blur and Rolling Shutter Effect
* Closed-Form Approximate CRF Training for Scalable Image Segmentation
* Closer Look at Context: From Coxels to the Contextual Emergence of Object Saliency, A
* Co-Sparse Textural Similarity for Interactive Segmentation
* Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment
* Collaborative Facial Landmark Localization for Transferring Annotations Across Datasets
* CollageParsing: Nonparametric Scene Parsing by Adaptive Overlapping Windows
* Comparing Salient Object Detection Results without Ground Truth
* ConceptMap: Mining Noisy Web Data for Concept Learning
* Consensus of Regression for Occlusion-Robust Facial Feature Localization
* Consistent Matting for Light Field Images
* Consistent Re-identification in a Camera Network
* Context as Supervisory Signal: Discovering Objects with Predictable Context
* Context-Based Pedestrian Path Prediction
* Continuous Conditional Neural Fields for Structured Regression
* Continuous Learning of Human Activity Models Using Deep Nets
* Contour Completion Model for Augmenting Surface Reconstructions, A
* Contrast Enhancement Framework with JPEG Artifacts Suppression, A
* Convergent Incoherent Dictionary Learning Algorithm for Sparse Coding, A
* Convexity Shape Prior for Segmentation
* Coplanar Common Points in Non-centric Cameras
* Correcting for Duplicate Scene Structure in Sparse 3D Reconstruction
* Creating Summaries from User Videos
* Crisp Boundary Detection Using Pointwise Mutual Information
* Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval
* Crowd Tracking with Dynamic Evolution of Group Structures
* DaMN: Discriminative and Mutually Nearest: Exploiting Pairwise Category Proximity for Video Action Recognition
* Deblurring Face Images with Exemplars
* Deep Features for Text Spotting
* Deep Learning of Scene-Specific Classifier for Pedestrian Detection
* Deep Network Cascade for Image Super-resolution
* Dense Semi-rigid Scene Flow Estimation from RGBD Images
* Depth Based Object Detection from Partial Pose Estimation of Symmetric Objects
* Depth-of-Field and Coded Aperture Imaging on XSlit Lens
* Description-Discrimination Collaborative Tracking
* Detecting Snap Points in Egocentric Video with a Web Photo Prior
* Detecting Social Actions of Fruit Flies
* Discovering Groups of People in Images
* Discovering Object Classes from Activities
* Discovering Video Clusters from Visual Features and Noisy Tags
* Discriminative Indexing for Probabilistic Image Patch Priors
* Discriminative Model with Multiple Temporal Scales for Action Prediction, A
* Discriminatively Trained Dense Surface Normal Estimation
* Distance Estimation of an Unknown Person from a Portrait
* Domain-Adaptive Discriminative One-Shot Learning of Gestures
* Duality and the Continuous Graphical Model
* Déjà Vu: Motion Prediction in Static Images
* Edge Boxes: Locating Object Proposals from Edges
* Efficient Color Constancy with Local Surface Reflectance Statistics
* Efficient Image and Video Co-Localization with Frank-Wolfe Algorithm
* Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation
* Efficient k-Support Matrix Pursuit
* Efficient Sparsity Estimation via Marginal-Lasso Coding
* Expanding the Family of Grassmannian Kernels: An Embedding Perspective
* Exploiting Low-Rank Structure from Latent Domains for Domain Generalization
* Exploiting Privileged Information from Web Data for Image Categorization
* Extended Lucas-Kanade Tracking
* Face Detection without Bells and Whistles
* Facial Landmark Detection by Deep Multi-task Learning
* Fast and Accurate Texture Recognition with Multilayer Convolution and Multifractal Analysis
* Fast and Simple Algorithm for Producing Candidate Regions, A
* Fast Visual Tracking via Dense Spatio-temporal Context Learning
* Feature Disentangling Machine: A Novel Approach of Feature Selection and Disentangling in Facial Expression Analysis
* Finding Approximate Convex Shapes in RGBD Images
* Finding Coherent Motions and Semantic Regions in Crowd Scenes: A Diffusion and Clustering Approach
* Food-101: Mining Discriminative Components with Random Forests
* Foreground Consistent Human Pose Estimation Using Branch and Bound
* FPM: Fine Pose Parts-Based Model with 3D CAD Models
* Free-Shape Polygonal Object Localization
* From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields
* From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices
* gDLS: A Scalable Solution to the Generalized Pose and Scale Problem
* Generalized Background Subtraction Using Superpixels with Label Integrated Motion Estimation
* Generalized Connectivity Constraints for Spatio-temporal 3D Reconstruction
* Generative Model for the Joint Registration of Multiple Point Sets, A
* Geodesic Object Proposals
* Geodesic Regression on the Grassmannian
* Geometric Calibration of Micro-Lens-Based Light Field Cameras Using Line Features
* Geometry Driven Semantic Labeling of Indoor Scenes
* GIS-Assisted Object Detection and Geospatial Localization
* Globally Optimal Inlier Set Maximization with Unknown Rotation and Focal Length
* Good Image Priors for Non-blind Deconvolution
* Graduated Consistency-Regularized Optimization for Multi-graph Matching
* Graph Cuts for Supervised Binary Coding
* Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid Generative-Descriptive Model, A
* Growing Regression Forests by Classification: Applications to Object Pose Estimation
* Hand Waving Away Scale
* Hierarchical Representation for Future Action Prediction, A
* Highly Overparameterized Optical Flow Using PatchMatch Belief Propagation
* Hipster Wars: Discovering Elements of Fashion Styles
* HiRF: Hierarchical Random Field for Collective Activity Recognition in Videos
* HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition
* Human Detection Using Learned Part Alphabet and Pose Dictionary
* Human Pose Estimation with Fields of Parts
* Hybrid Image Deblurring by Fusing Edge and Power Spectrum Information
* Hybrid Stochastic / Deterministic Optimization for Tracking Sports Players and Pedestrians
* Image Deconvolution Ringing Artifact Detection and Removal via PSF Frequency Analysis
* Image Retrieval and Ranking via Consistently Reconstructing Multi-attribute Queries
* Image Tag Completion by Noisy Matrix Recovery
* Image-Based 4-d Reconstruction Using 3-d Change Detection
* Improved Motion Invariant Deblurring through Motion Estimation
* Improving Image-Sentence Embeddings Using Large Weakly Annotated Photo Collections
* Instance Segmentation of Indoor Scenes Using a Coverage Loss
* Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model
* Interactive Object Counting
* Interactively Guiding Semi-Supervised Clustering via Attribute-Based Explanations
* Interestingness Prediction by Robust Learning to Rank
* Interreflection Removal Using Fluorescence
* Intrinsic Face Image Decomposition with Human Face Priors
* Intrinsic Image Decomposition Using Structure-Texture Separation and Surface Normals
* Intrinsic Textures for Relightable Free-Viewpoint Video
* Intrinsic Video
* Inverse Kernels for Fast Spatial Deconvolution
* Joint Cascade Face Detection and Alignment
* Joint Object Class Sequencing and Trajectory Triangulation (JOST)
* Joint Semantic Segmentation and 3D Reconstruction from Monocular Video
* Joint Unsupervised Face Alignment and Behaviour Analysis
* Jointly Optimizing 3D Model Fitting and Fine-Grained Classification
* Know Your Limits: Accuracy of Long Range Stereoscopic Object Measurements in Practice
* Knowing a Good HOG Filter When You See It: Efficient Selection of Filters for Detection
* Large Margin Local Metric Learning
* Large-Scale Object Classification Using Label Relation Graphs
* Latent-Class Hough Forests for 3D Object Detection and Pose Estimation
* Learning 6D Object Pose Estimation Using 3D Object Coordinates
* Learning a Deep Convolutional Network for Image Super-Resolution
* Learning Brightness Transfer Functions for the Joint Recovery of Illumination Changes and Optical Flow
* Learning Discriminative and Shareable Features for Scene Classification
* Learning Graphs to Model Visual Objects across Different Depictive Styles
* Learning High-Level Judgments of Urban Perception
* Learning Latent Constituents for Recognition of Group Activities in Video
* Learning Rich Features from RGB-D Images for Object Detection and Segmentation
* Learning the Face Prior for Bayesian Face Recognition
* Learning to Hash with Partial Tags: Exploring Correlation between Tags and Hashing Bits for Large Scale Image Retrieval
* Learning to Rank 3D Features
* Learning to Rank Using High-Order Information
* Learning Where to Classify in Multi-view Semantic Segmentation
* Let There Be Color! Large-Scale Texturing of 3D Reconstructions
* Linking People in Videos with Their Names Using Coreference Resolution
* Local Estimation of High Velocity Optical Flow with Correlation Image Sensor
* LSD-SLAM: Large-Scale Direct Monocular SLAM
* MAP-Estimation Framework for Blind Deblurring Using High-Level Edge Priors, A
* Match Selection and Refinement for Highly Accurate Two-View Structure from Motion
* Material Classification Based on Training Data Synthesized Using a BTF Database
* MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization
* Metric-Based Pairwise and Multiple Image Registration
* Microsoft COCO: Common Objects in Context
* Model Selection by Linear Programming
* Model-Free Segmentation and Grasp Selection of Unknown Stacked Objects
* Modeling Blurred Video with Layers
* Modeling Perceptual Color Differences by Local Metric Learning
* Modeling Video Dynamics with Deep Dynencoder
* Monocular Multiview Object Tracking with 3D Aspect Parts
* Motion Words for Videos
* Movement Pattern Histogram for Action Recognition and Retrieval
* Multi Focus Structured Light for Recovering Scene Shape and Global Illumination
* Multi-body Depth-Map Fusion with Non-intersection Constraints
* Multi-class Open Set Recognition Using Probability of Inclusion
* Multi-level Adaptive Active Learning for Scene Classification
* Multi-modal and Multi-spectral Registration for Natural Images
* Multi-modal Unsupervised Feature Learning for RGB-D Scene Labeling
* Multi-scale Orderless Pooling of Deep Convolutional Activation Features
* Multi-stage Approach to Curve Extraction, A
* Multi-transformational Model for Background Subtraction with Moving Cameras, A
* Multilinear Wavelets: A Statistical Shape Space for Human Faces
* Natural Action Recognition Using Invariant 3D Motion Encoding
* Neural Codes for Image Retrieval
* New Variational Framework for Multiview Surface Reconstruction, A
* Non-associative Higher-Order Markov Networks for Point Cloud Classification
* Non-Linear Filter for Gyroscope-Based Video Stabilization, A
* Non-local Method for Robust Noisy Image Completion, A
* Non-local Total Generalized Variation for Optical Flow Estimation
* Non-parametric Higher-Order Random Fields for Image Segmentation
* Nonrigid Surface Registration and Completion from RGBD Images
* Novel Topic-Level Random Walk Framework for Scene Image Co-segmentation, A
* Numerical Inversion of SRNFs for Efficient Elastic Shape Analysis of Star-Shaped Objects
* Object Co-detection via Efficient Inference in a Fully-Connected CRF
* Object Detection and Viewpoint Estimation with Auto-masking Neural Network
* Occlusion and Motion Reasoning for Long-Term Tracking
* On Image Contours of Projective Shapes
* On Mean Pose and Variability of 3D Deformable Models
* On Sampling Focal Length Values to Solve the Absolute Pose Problem
* On Shape and Material Recovery from Motion
* Online Graph-Based Tracking
* Online, Real-Time Tracking Using a Category-to-Individual Detector
* OpenDR: An Approximate Differentiable Renderer
* Optical Flow Estimation with Channel Constancy
* Optimal Essential Matrix Estimation via Inlier-Set Maximization
* Optimization-Based Artifact Correction for Electron Microscopy Image Stacks
* Optimizing Ranking Measures for Compact Binary Code Learning
* Orientation Covariant Aggregation of Local Descriptors with Embeddings
* OTC: A Novel Local Descriptor for Scene Classification
* Pairwise Probabilistic Voting: Fast Place Recognition without RANSAC
* PanoContext: A Whole-Room 3D Context Model for Panoramic Scene Understanding
* Parameterizing Object Detectors in the Continuous Pose Space
* Part Bricolage: Flow-Assisted Part-Based Graphs for Detecting Activities in Videos
* Part-Based R-CNNs for Fine-Grained Category Detection
* Part-Pair Representation for Part Localization
* Passive Tomography of Turbulence Strength
* Perceptually Inspired Layout-Aware Losses for Image Segmentation
* Person Re-identification by Video Ranking
* Person Re-Identification Using Kernel-Based Metric Learning Methods
* Photo Uncrop
* Physically Grounded Spatio-temporal Object Affordances
* Piecewise-Planar StereoScan: Structure and Motion from Plane Primitives
* Pipe-Run Extraction and Reconstruction from Point Clouds
* Pipelining Localized Semantic Features for Fine-Grained Action Recognition
* Planar Structure Matching under Projective Uncertainty for Geolocation
* Pose Filter Based Hidden-CRF Models for Activity Detection
* Pose Locality Constrained Representation for 3D Human Pose Reconstruction
* Pose Machines: Articulated Pose Estimation via Inference Machines
* Pot of Gold: Rainbows as a Calibration Cue, A
* Precision-Recall-Classification Evaluation Framework: Application to Depth Estimation on Single Images
* Predicting Actions from Static Scenes
* Probabilistic Temporal Head Pose Estimation Using a Hierarchical Graphical Model
* Programmable Automotive Headlights
* Progressive Mode-Seeking on Graphs for Sparse Feature Matching
* Pseudo-bound Optimization for Binary Energies
* Radial Bright Channel Prior for Single Image Vignetting Correction
* Rank Minimization with Structured Data Patterns
* Ranking Domain-Specific Highlights by Analyzing Edited Videos
* Read My Lips: Continuous Signer Independent Weakly Supervised Viseme Recognition
* Real-Time Exemplar-Based Face Sketch Synthesis
* Real-Time Minimization of the Piecewise Smooth Mumford-Shah Functional
* Reasoning about Object Affordances in a Knowledge Base Representation
* Recognizing City Identity via Attribute Analysis of Geo-tagged Images
* Recognizing Complex Events in Videos by Learning Key Static-Dynamic Evidences
* Recognizing Products: A Per-exemplar Multi-Label Image Classification Approach
* Recovering Scene Geometry under Wavy Fluid via Distortion and Defocus Analysis
* Refraction Wiggles for Measuring Fluid Depth and Velocity from Video
* Reverse Training: An Efficient Approach for Image Set Classification
* RGBD Salient Object Detection: A Benchmark and Algorithms
* Riemannian Sparse Coding for Positive Definite Matrices
* Robust and Accurate Non-parametric Estimation of Reflectance Using Basis Decomposition and Correction Functions
* Robust Bundle Adjustment Revisited
* Robust Foreground Detection Using Smoothness and Arbitrariness Constraints
* Robust Global Translations with 1DSfM
* Robust Instance Recognition in Presence of Occlusion and Clutter
* Robust Motion Segmentation with Unknown Correspondences
* Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees
* Robust Sparse Coding and Compressed Sensing with the Difference Map
* Robust Visual Tracking with Double Bounding Box Model
* ROCHADE: Robust Checkerboard Advanced Detection for Camera Calibration
* Rolling Guidance Filter
* Saliency Detection with Flash and No-flash Image Pairs
* Saliency in Crowd
* Salient Color Names for Person Re-identification
* Salient Montages from Unconstrained Videos
* Scalable 6-DOF Localization on Mobile Devices
* Scene Chronology
* Scene Classification via Hypergraph-Based Semantic Attributes Subnetworks Identification
* Schwarps: Locally Projective Image Warps Based on 2D Schwarzian Derivatives
* Seeing is Worse than Believing: Reading People's Minds Better than Computer-Vision Methods Recognize Actions
* Selecting Influential Examples: Active Learning with Expected Model Output Changes
* Self-explanatory Sparse Representation for Image Classification
* Semantic Aware Video Transcription Using Random Forest Classifiers
* Separable Spatiotemporal Priors for Convex Reconstruction of Time-Varying 3D Point Clouds
* Sequential Max-Margin Event Detectors
* Shape from Light Field Meets Robust PCA
* ShapeForest: Building Constrained Statistical Shape Models with Decision Trees
* Shrinkage Expansion Adaptive Metric Learning
* Similarity-Invariant Sketch-Based Image Retrieval in Large Databases
* Simultaneous Detection and Segmentation
* Simultaneous Feature and Dictionary Learning for Image Set Based Face Recognition
* Single-Image Super-Resolution: A Benchmark
* Sliding Shapes for 3D Object Detection in Depth Images
* Soft Cost Aggregation with Multi-resolution Fusion
* Solving Square Jigsaw Puzzles with Loop Constraints
* SPADE: Scalar Product Accelerator by Integer Decomposition for Object Detection
* Sparse Additive Subspace Clustering
* Sparse Dictionaries for Semantic Segmentation
* Sparse Spatio-spectral Representation for Hyperspectral Image Super-resolution
* Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
* Spatio-chromatic Opponent Features
* Spatio-temporal Event Classification Using Time-Series Kernel Based Structured Sparsity
* Spatio-temporal Matching for Human Detection in Video
* Spatio-temporal Object Detection Proposals
* Spatiotemporal Background Subtraction Using Minimum Spanning Tree and Optical Flow
* Spectra Estimation of Fluorescent and Reflective Scenes by Using Ordinary Illuminants
* Spectral Clustering with a Convex Regularizer on Millions of Images
* Spectral Edge Image Fusion: Theory and Applications
* SRA: Fast Removal of General Multipath for ToF Sensors
* Stacked Deformable Part Model with Shape Regression for Object Part Localization
* Statistical and Spatial Consensus Collection for Detector Adaptation
* Statistical Pose Averaging with Non-isotropic and Incomplete Relative Measurements
* Stixmantics: A Medium-Level Model for Real-Time Semantic Scene Understanding
* Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features
* Sub-pixel Layout for Super-Resolution with Images in the Octic Group
* Superior Tracking Approach: Building a Strong Tracker through Fusion, A
* Superpixel Graph Label Transfer with Learned Distance Metric
* Supervoxel-Consistent Foreground Propagation in Video
* Support Vector Guided Dictionary Learning
* Surface Matching and Registration by Landmark Curve-Driven Canonical Quasiconformal Mapping
* Surface Normal Deconvolution: Photometric Stereo for Optically Thick Translucent Objects
* Synchronization of Two Independently Moving Cameras without Feature Correspondences
* Total Moving Face Reconstruction
* Towards Transparent Systems: Semantic Characterization of Failure Modes
* Towards Unified Object Detection and Semantic Segmentation
* Tracking Interacting Objects Optimally Using Integer Programming
* Tracking Using Multilevel Quantizations
* Tractable and Reliable Registration of 2D Point Sets
* Training Deformable Object Models for Human Detection Based on Alignment and Clustering
* Training Object Class Detectors from Eye Tracking Data
* Training-Based Spectral Reconstruction from a Single RGB Image
* Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation
* Transfer Learning Based Visual Tracking with Gaussian Processes Regression
* Tubular Structure Filtering by Ranking Orientation Responses of Path Operators
* Unfolding an Indoor Origami World
* Unsupervised Dense Object Discovery, Detection, Tracking and Reconstruction
* Unsupervised Video Adaptation for Parsing Human Motion
* Untangling Object-View Manifold for Multiview Recognition and Pose Estimation
* UPnP: An Optimal O(n) Solution to the Absolute Pose Problem with Universal Applicability
* Using Isometry to Classify Correct/Incorrect 3D-2D Correspondences
* VCDB: A Large-Scale Database for Partial Copy Detection in Videos
* Video Action Detection with Relational Dynamic-Poselets
* Video Object Co-segmentation by Regulated Maximum Weight Cliques
* Video Object Discovery and Co-Segmentation with Extremely Weak Supervision
* Video Pop-up: Monocular 3D Reconstruction of Dynamic Scenes
* Video Registration to SfM Models
* View-Consistent 3D Scene Flow Estimation over Multiple Frames
* Visual Tracking by Sampling Tree-Structured Graphical Models
* Visualizing and Understanding Convolutional Networks
* VocMatch: Efficient Multiview Correspondence for Structure from Motion
* Weakly Supervised Action Labeling in Videos under Ordering Constraints
* Weakly Supervised Learning of Objects, Attributes and Their Associations
* Weakly Supervised Object Localization with Latent Category Learning
* Webpage Saliency
* Weighted Block-Sparse Low Rank Representation for Face Clustering in Videos
* Well Begun Is Half Done: Generating High-Quality Seeds for Automatic Image Dataset Construction from Web
* What Do I See? Modeling Human Visual Perception for Multi-person Tracking
* Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization
* Zero-Shot Learning via Visual Abstraction
363 for ECCV14

ECCV16 * *ECCV
* 3D Image Reconstruction from X-Ray Measurements with Overlap
* 3D Mask Face Anti-spoofing with Remote Photoplethysmography
* 3D Morphable Eye Region Model for Gaze Estimation, A
* 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
* 4D Light-Field Dataset and CNN Architectures for Material Recognition, A
* 4D Match Trees for Non-rigid Surface Alignment
* Abundant Inverse Regression Using Sufficient Reduction and Its Applications
* Accelerating Convolutional Neural Networks with Dominant Convolutional Kernel and Knowledge Pre-regression
* Accelerating the Super-Resolution Convolutional Neural Network
* Accurate and Linear Time Pose Estimation from Points and Lines
* ActionSnapping: Motion-Based Video Synchronization
* Adaptive Signal Recovery on Graphs via Harmonic Analysis for Experimental Design in Neuroimaging
* All-Around Depth from Small Motion with a Spherical Panoramic Camera
* Ambient Sound Provides Supervision for Visual Learning
* Amodal Instance Segmentation
* Angry Crowds: Detecting Violent Events in Videos
* Approximate Search with Quantized Sparse Representations
* Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering
* ATGV-Net: Accurate Depth Super-Resolution
* Attribute2Image: Conditional Image Generation from Visual Attributes
* Augmented Feedback in Semantic Segmentation Under Image Level Supervision
* Automatic Attribute Discovery with Neural Activations
* Automatically Selecting Inference Algorithms for Discrete Energy Minimisation
* Bayesian Image Based 3D Pose Estimation
* Benchmark and Simulator for UAV Tracking, A
* Benchmark for Automatic Visual Classification of Clinical Skin Disease Images, A
* Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
* Biconvex Relaxation for Semidefinite Programming in Computer Vision
* Binary Hashing with Semidefinite Relaxation and Augmented Lagrangian
* Branching Gaussian Processes with Applications to Spatiotemporal Reconstruction of 3D Trees
* Branching Path Following for Graph Matching
* Building Dual-Domain Representations for Compression Artifacts Reduction
* Building Scene Models by Completing and Hallucinating Depth and Semantics
* Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
* Can We Jointly Register and Reconstruct Creased Surfaces by Shape-from-Template Accurately?
* Capturing Dynamic Textured Surfaces of Moving Targets
* Carried Object Detection Based on an Ensemble of Contour Exemplars
* Cascaded Continuous Regression for Real-Time Incremental Face Tracking
* CATS: Co-saliency Activated Tracklet Selection for Video Co-Localization
* CDT: Cooperative Detection and Tracking for Tracing Multiple Objects in Video Sequences
* Chained Predictions Using Convolutional Neural Networks
* Cluster Sampling Method for Image Matting via Sparse Coding, A
* Cluster Sparsity Field for Hyperspectral Imagery Denoising
* CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
* Coarse-to-fine Planar Regularization for Dense Monocular Depth Estimation
* COCO Attributes: Attributes for People, Animals, and Objects
* Collaborative Layer-Wise Discriminative Learning in Deep Neural Networks
* Colorful Image Colorization
* Complexity of Discrete Energy Minimization Problems
* Conditional Lucas & Kanade Algorithm, The
* Connectionist Temporal Modeling for Weakly Supervised Action Labeling
* ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
* Contextual Priming and Feedback for Faster R-CNN
* Continuous Optimization Approach for Efficient and Accurate Scene Flow, A
* Convex Solution to Spatially-Regularized Correspondence Problems, A
* Convolutional Oriented Boundaries
* Counting in the Wild
* Cross-Modal Supervision for Learning Active Speaker Detection in Video
* Crossing-Line Crowd Counting with Two-Phase Deep Neural Networks
* Curious Robot: Learning Visual Representations via Physical Interactions, The
* DAPs: Deep Action Proposals for Action Understanding
* DAVE: A Unified Framework for Fast Vehicle Detection and Annotation
* Deep Attributes Driven Multi-camera Person Re-identification
* Deep Automatic Portrait Matting
* Deep Cascaded Bi-Network for Face Hallucination
* Deep Decoupling of Defocus and Motion Blur for Dynamic Segmentation
* Deep Deformation Network for Object Landmark Localization
* Deep Image Retrieval: Learning Global Representations for Image Search
* Deep Joint Image Filtering
* Deep Learning 3D Shape Surfaces Using Geometry Images
* Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation
* Deep Learning the City: Quantifying Urban Perception at a Global Scale
* Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance, A
* Deep Markov Random Field for Image Modeling
* Deep Networks with Stochastic Depth
* Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
* Deep Robust Encoder Through Locality Preserving Low-Rank Dictionary
* Deep Self-correlation Descriptor for Dense Cross-Modal Correspondence
* Deep Specialized Network for Illuminant Estimation
* Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks
* DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model
* DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation
* Degeneracies in Rolling Shutter SfM
* Depth Map Super-Resolution by Deep Multi-Scale Guidance
* Depth-Aware Motion Magnification
* Design of Kernels in Convolutional Neural Networks for Image Classification
* Detecting Engagement in Egocentric Video
* Detecting Text in Natural Image with Connectionist Text Proposal Network
* Diagram is Worth a Dozen Images, A
* Discriminative Feature Learning Approach for Deep Face Recognition, A
* Discriminative Framework for Anomaly Detection in Large Videos, A
* Distance for HMMs Based on Aggregated Wasserstein Metric and State Registration, A
* Distinct Class-Specific Saliency Maps for Weakly Supervised Semantic Segmentation
* Distractor-Supported Single Target Tracking in Extremely Cluttered Scenes
* Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
* DOC: Deep OCclusion Estimation from a Single Image
* Domain Adaptive Fisher Vector for Visual Recognition
* Double-Opponent Vectorial Total Variation
* Dual Structured Light 3D Using a 1D Sensor
* Efficient and Robust Semi-supervised Learning Over a Sparse-Regularized Graph
* Efficient Continuous Relaxations for Dense CRF
* Efficient Fusion Move Algorithm for the Minimum Cost Lifted Multicut Problem, An
* Efficient Large Scale Image Classification via Prediction Score Decomposition
* Efficient Multi-frequency Phase Unwrapping Using Kernel Density Estimation
* Efficient Multi-view Surface Refinement with Adaptive Resolution Control
* Ego2Top: Matching Viewers in Egocentric and Top-View Videos
* Eigen Appearance Maps of Dynamic Shapes
* Embedding Deep Metric for Person Re-identification: A Study Against Large Variations
* Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild, An
* End-to-End Localization and Ranking for Relative Attributes
* Estimation of Human Body Shape in Motion with Wide Clothing
* Evaluation of Computational Imaging Techniques for Heterogeneous Inverse Scattering, An
* Evaluation of LBP and Deep Texture Descriptors with a New Robustness Benchmark
* Exploiting Semantic Information and Deep Matching for Optical Flow
* Extending Long Short-Term Memory for Multi-View Structured Learning
* Face Detection with End-to-End Integration of a ConvNet and a 3D Model
* Face Recognition Using a Unified 3D Morphable Model
* Faceless Person Recognition: Privacy Implications in Social Media
* Facilitating and Exploring Planar Homogeneous Texture for Indoor Scene Understanding
* Fashion Landmark Detection in the Wild
* Fast 6D Pose Estimation from a Monocular Image Using Hierarchical Pose Trees
* Fast Bilateral Solver, The
* Fast Global Registration
* Fast Guided Global Interpolation for Depth and Motion
* Fast Optical Flow Using Dense Inverse Search
* Fast, Exact and Multi-scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
* FigureSeer: Parsing Result-Figures in Research Papers
* Fine-Grained Material Classification Using Micro-geometry and Reflectance
* Fine-Scale Surface Normal Estimation Using a Single NIR Image
* Focal Flow: Measuring Distance and Velocity with Defocus and Differential Motion
* Foreground Segmentation via Dynamic Tree-Structured Sparse RPCA
* Friction from Reflectance: Deep Reflectance Codes for Predicting Physical Surface Properties from One-Shot In-Field Reflectance
* From Multiview Image Curves to 3D Drawings
* Fundamental Matrices from Moving Objects Using Line Motion Barcodes
* Gated Bi-Directional CNN for Object Detection
* Gated Siamese Convolutional Neural Network Architecture for Human Re-identification
* Gaussian Process Density Counting from Weak Supervision
* General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues
* Generalized Successive Shortest Paths Solver for Tracking Dividing Targets, A
* Generating Visual Explanations
* Generative Image Modeling Using Style and Structure Adversarial Networks
* Generative Visual Manipulation on the Natural Image Manifold
* Generic 3D Representation via Pose Estimation and Matching
* Geometric Approach to Image Labeling, A
* Geometric Neural Phrase Pooling: Modeling the Spatial Co-Occurrence of Neurons
* Global Registration of 3D Point Sets via LRS Decomposition
* Globally Continuous and Non-Markovian Crowd Activity Analysis from Videos
* Going Further with Point Pair Features
* Graph Based Skeleton Motion Representation and Similarity Measurement for Action Recognition
* Graph-Based Consistent Matching for Structure-from-Motion
* Grid Loss: Detecting Occluded Faces
* Grounding of Textual Phrases in Images by Reconstruction
* Guided Matching Based on Statistical Optical Flow for Fast and Robust Correspondence Analysis
* Hand Pose Estimation from Local Surface Normals
* Head Reconstruction from Internet Photos
* Heat Diffusion Long-Short Term Memory Learning for 3D Shape Analysis
* HFS: Hierarchical Feature Selection for Efficient Image Segmentation
* Hierarchical Beta Process with Gaussian Process Prior for Hyperspectral Image Super Resolution
* Hierarchical Dynamic Parsing and Encoding for Action Recognition
* Higher Order Conditional Random Fields in Deep Neural Networks
* Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
* HouseCraft: Building Houses from Rental Ads and Street Views
* Human Attribute Recognition by Deep Hierarchical Contexts
* Human Pose Estimation Using Deep Consensus Voting
* Human Pose Estimation via Convolutional Part Heatmap Regression
* Human Re-identification in Crowd Videos Using Personal, Social and Environmental Constraints
* Human-in-the-Loop Person Re-identification
* Identity Mappings in Deep Residual Networks
* Image Co-Localization by Mimicking a Good Detector's Confidence Score Distribution
* Image Co-segmentation Using Maximum Common Subgraph Matching and Region Co-growing
* Image Quality Assessment Using Similar Scene as Reference
* Improving Multi-frame Data Association with Sparse Representations for Robust Near-online Multi-object Tracking
* Improving Multi-label Learning with Missing Labels by Structured Semantic Correlations
* Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classiffication
* Individualness and Determinantal Point Processes for Pedestrian Detection
* Indoor-Outdoor 3D Reconstruction Alignment
* Information Bottleneck Domain Adaptation with Privileged Information for Visual Recognition
* Instance-Sensitive Fully Convolutional Networks
* Integration of Probabilistic Pose Estimates from Multiple Views
* Inter-battery Topic Representation Learning
* Interactive Image Segmentation Using Constrained Dominant Sets
* Interpreting the Ratio Criterion for Matching SIFT Descriptors
* Is Faster R-CNN Doing Well for Pedestrian Detection?
* It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos
* Iterative Reference Driven Metric Learning for Signer Independent Isolated Sign Language Recognition
* Jensen Bregman LogDet Divergence Optimal Filtering in the Manifold of Positive Definite Matrices
* Joint Face Alignment and 3D Face Reconstruction
* Joint Face Representation Adaptation and Clustering in Videos
* Joint Learning of Semantic and Latent Attributes
* Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
* Kernel-Based Supervised Discrete Hashing for Image Retrieval
* Kernelized Subspace Ranking for Saliency Detection
* Knowledge Transfer for Scene-Specific Motion Prediction
* L0-Sparse Subspace Clustering
* Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
* Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning, A
* Large Scale Asset Extraction for Urban Images
* Large-Scale R-CNN with Classifier Adaptive Quantization
* Large-Scale Training of Shadow Detectors with Noisily-Annotated Shadow Examples
* Learnable Histogram: Statistical Context Features for Deep Neural Networks
* Learning a Predictable and Generative Vector Representation for Objects
* Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks
* Learning Diverse Models: The Coulomb Structured Support Vector Machine
* Learning Dynamic Hierarchical Models for Anytime Scene Labeling
* Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs
* Learning Image Matching by Simply Watching Video
* Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering
* Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network
* Learning Representations for Automatic Colorization
* Learning Semantic Deformation Flows with 3D Convolutional Networks
* Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes
* Learning Temporal Transformations from Time-Lapse Videos
* Learning to Count with CNN Boosting
* Learning to Hash with Binary Deep Neural Network
* Learning to Learn: Model Regression Networks for Easy Small Sample Learning
* Learning to Refine Object Segments
* Learning to Track at 100 FPS with Deep Regression Networks
* Learning Visual Features from Large Weakly Supervised Data
* Learning Visual Storylines with Skipping Recurrent Neural Networks
* Learning Without Forgetting
* Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video
* Less Is More: Towards Compact CNNs
* Leveraging Visual Question Answering for Image-Caption Ranking
* LIFT: Learned Invariant Feature Transform
* Light Field Segmentation Using a Ray-Based Graph Structure
* Linear Depth Estimation from an Uncalibrated, Monocular Polarisation Image
* Localizing and Orienting Street Views Using Overhead Imagery
* Look-Ahead Before You Leap: End-to-End Active Recognition by Forecasting the Effect of Motion
* LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling
* MADMM: A Generic Algorithm for Non-smooth Optimization on Manifolds
* Manhattan-World Urban Reconstruction from Point Clouds
* Marker-Less 3D Human Motion Capture with Monocular Image Sequence and Height-Maps
* MARLow: A Joint Multiplanar Autoregressive and Low-Rank Approach for Image Completion
* MARS: A Video Benchmark for Large-Scale Person Re-Identification
* Matching Handwritten Document Images
* MeshFlow: Minimum Latency Online Video Stabilization
* Minimal Solution for Non-perspective Pose Estimation from Line Correspondences, A
* Minimal Solvers for Generalized Pose and Scale Estimation from Two Rays and One Point
* Modeling Context Between Objects for Referring Expression Understanding
* Modeling Context in Referring Expressions
* MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes
* MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
* Multi-attributed Graph Matching with Multi-layer Random Walks
* Multi-label Active Learning Based on Maximum Correntropy Criterion: Towards Robust and Discriminative Labeling
* Multi-region Two-Stream R-CNN for Action Detection
* Multi-scale CNN for Affordance Segmentation in RGB Images, A
* Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation
* Multi-view 3D Models from Single Images with a Convolutional Network
* Multi-view Inverse Rendering Under Arbitrary Illumination and Albedo
* Natural Image Matting Using Deep Convolutional Neural Networks
* Natural Image Stitching with the Global Similarity Prior
* Network Flow Formulations for Learning Binary Hashing
* Network of Experts for Large-Scale Image Categorization
* Neural Approach to Blind Motion Deblurring, A
* Non-rigid 3D Shape Retrieval via Large Margin Nearest Neighbor Embedding
* Normalized Cut Meets MRF
* Novel Coplanar Line-Points Invariants for Robust Line Matching Across Views
* Novel Tiny Object Recognition Algorithm Based on Unit Statistical Curvature Feature, A
* ObjectNet3D: A Large Scale Database for 3D Object Recognition
* Occlusion-Resistant Ellipse Detection Method by Joining Coelliptic Arcs, An
* On Volumetric Shape Reconstruction from Implicit Forms
* Online Action Detection
* Online Adaptation for Joint Scene and Object Classification
* Online Human Action Detection Using Joint Classification-Regression Recurrent Neural Networks
* Online Variational Bayesian Motion Averaging
* Partial Linearization Based Optimization for Multi-class SVM
* Patch-Based Low-Rank Matrix Completion for Learning of Shape and Motion Models from Few Training Samples
* Pattern Mining Saliency
* Peak-Piloted Deep Network for Facial Expression Recognition
* Pedestrian Behavior Understanding and Prediction with Deep Neural Networks
* Perceptual Losses for Real-Time Style Transfer and Super-Resolution
* Peripheral Expansion of Depth Information via Layout Estimation with Fisheye Camera
* Person Re-Identification by Unsupervised L1 Graph Learning
* Person Re-identification via Recurrent Feature Aggregation
* Phase-Based Modification Transfer for Video
* Photo Aesthetics Ranking Network with Attributes and Content Adaptation
* Photometric Stereo Under Non-uniform Light Intensities and Exposures
* pi-Match: Monocular vSLAM and Piecewise Planar Reconstruction Using Fast Plane Correspondences
* Pixel-Level Domain Transfer
* Pixelwise View Selection for Unstructured Multi-View Stereo
* PlaNet: Photo Geolocation with Convolutional Neural Networks
* Playing for Data: Ground Truth from Computer Games
* Polysemous Codes
* Pose Estimation Errors, the Ultimate Diagnosis
* Pose Hashing with Microlens Arrays
* Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
* Projective Bundle Adjustment from Arbitrary Initialization Using the Variable Projection Method
* Pseudo-geometric Formulation for Fitting Equidistant Parallel Lines
* Query-Focused Extractive Video Summarization
* Real-Time 3D Reconstruction and 6-DoF Tracking with an Event Camera
* Real-Time Facial Segmentation and Performance Capture from RGB Input
* Real-Time Joint Tracking of a Hand Manipulating an Object from RGB-D Input
* Real-Time Large-Scale Dense 3D Reconstruction with Loop Closure
* Real-Time Monocular Segmentation and Pose Tracking of Multiple Objects
* Real-Time RGB-D Activity Prediction by Soft Regression
* Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning
* Recognition from Hand Cameras: A Revisit with Deep Learning
* Recurrent Encoder-Decoder Network for Sequential Face Alignment, A
* Recurrent Instance Segmentation
* Recurrent Temporal Deep Field for Semantic Video Labeling
* Reflection Symmetry Detection via Appearance of Structure Descriptor
* Region-Based Semantic Segmentation with End-to-End Training
* Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks
* Reliable Attribute-Based Object Recognition Using High Predictive Value Classifiers
* Reliable Fusion of ToF and Stereo Depth Driven by Confidence Measures
* RepMatch: Robust Feature Matching and Pose for Reconstructing Modern Cities
* Resonant Deformable Matching: Simultaneous Registration and Reconstruction
* Revisiting Additive Quantization
* Revisiting Visual Question Answering Baselines
* RNN Fisher Vectors for Action Recognition and Image Annotation
* Robust and Accurate Line- and/or Point-Based Pose Estimation without Manhattan Assumptions
* Robust Face Alignment Using a Mixture of Invariant Experts
* Robust Facial Landmark Detection via Recurrent Attentive-Refinement Networks
* Robust Image and Video Dehazing with Visual Artifact Suppression via Gradient Residual Minimization
* Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs
* Saliency Detection with Recurrent Fully Convolutional Networks
* Salient Deconvolutional Networks
* Scalable Metric Learning via Weighted Approximate Rank Component Analysis
* Scene Depth Profiling Using Helmholtz Stereopsis
* SDF-2-SDF: Highly Accurate 3D Object Reconstruction
* SEAGULL: Seam-Guided Local Alignment for Parallax-Tolerant Image Stitching
* Search-Based Depth Estimation via Coupled Dictionary Learning with Large-Margin Structure Inference
* Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation
* Segmental Spatiotemporal CNNs for Fine-Grained Action Segmentation
* Segmentation from Natural Language Expressions
* Semantic 3D Reconstruction of Heads
* Semantic Clustering for Robust Fine-Grained Scene Recognition
* Semantic Co-segmentation in Videos
* Semantic Object Parsing with Graph LSTM
* Semi-supervised Learning Based on Joint Diffusion of Graph Functions and Laplacians
* Sequential Approach to 3D Human Pose Estimation: Separation of Localization and Identification of Body Joints, A
* Shading-Aware Multi-view Stereo
* Shape Acquisition and Registration for 3D Endoscope Based on Grid Pattern Projection
* Shape from Selfies: Human Body Shape Estimation Using CCA Regression Forests
* Shape from Water: Bispectral Light Absorption for Depth Recovery
* Shape-Based Approach for Salient Object Detection Using Deep Learning, A
* ShapeFit and ShapeKick for Robust, Scalable Structure from Motion
* Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification
* Siamese Long Short-Term Memory Architecture for Human Re-identification, A
* Similarity Registration Problems for 2D/3D Ultrasound Calibration
* Simple Hierarchical Pooling Data Structure for Loop Closure, A
* Single Image 3D Interpreter Network
* Single Image Dehazing via Multi-Scale Convolutional Neural Networks
* Smooth Neighborhood Structure Mining on Multiple Affinity Graphs with Applications to Context-Sensitive Similarity
* Software Platform for Manipulating the Camera Imaging Pipeline, A
* Sparse Recovery of Hyperspectral Signal from Natural RGB Images
* Sparse Representation Based Complete Kernel Marginal Fisher Analysis Framework for Computational Art Painting Categorization
* Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation
* Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition
* Spatio-Temporally Consistent Correspondence for Dense Dynamic Scene Modeling
* SPICE: Semantic Propositional Image Caption Evaluation
* SPLeaP: Soft Pooling of Learned Parts for Image Classification
* Spot On: Action Localization from Pointly-Supervised Proposals
* SSD: Single Shot MultiBox Detector
* SSHMT: Semi-supervised Hierarchical Merge Tree for Electron Microscopy Image Segmentation
* Stacked Hourglass Networks for Human Pose Estimation
* Stereo Video Deblurring
* Stochastic Dykstra Algorithms for Metric Learning with Positive Definite Covariance Descriptors
* Streaming Video Segmentation via Short-Term Hierarchical Segmentation and Frame-by-Frame Markov Random Field Optimization
* Structure from Motion on a Sphere
* Structured Matching for Phrase Localization
* Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies
* Superpixel Convolutional Networks Using Bilateral Inceptions
* Superpixel-Based Two-View Deterministic Fitting for Multiple-Structure Data
* Supervised Transformer Network for Efficient Face Detection
* Support Discrimination Dictionary Learning for Image Classification
* SurfCut: Free-Boundary Surface Extraction
* SyB3R: A Realistic Synthetic Benchmark for 3D Reconstruction from Images
* Symmetric Non-rigid Structure from Motion for Category-Specific Object Structure Estimation
* Symmetry Prior for Convex Variational 3D Reconstruction, A
* Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition
* Target Response Adaptation for Correlation Filter Tracking
* Taxonomy-Regularized Semantic Deep Convolutional Neural Networks
* Template-Free 3D Reconstruction of Poorly-Textured Nonrigid Surfaces
* Temporal Model Adaptation for Person Re-identification
* Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
* Temporally Robust Global Motion Compensation by Keypoint-Based Congealing
* Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons
* Title Generation for User Generated Videos
* Top-Down Learning for Structured Labeling with Convolutional Pseudoprior
* Top-Down Neural Attention by Excitation Backprop
* Towards Large-Scale City Reconstruction from Satellites
* Towards Perspective-Free Object Counting with Deep Learning
* Towards Viewpoint Invariant 3D Human Pose Estimation
* Tracking Completion
* Tracking Persons-of-Interest via Adaptive Discriminative Features
* Transfer Neural Trees for Heterogeneous Domain Adaptation
* Ultra-Resolving Face Images by Discriminative Generative Networks
* Uncertain Future: Forecasting from Static Images Using Variational Autoencoders, An
* Uncovering Symmetries in Polynomial Systems
* Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields
* Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection, A
* Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition, The
* Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
* Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
* Unsupervised Visual Representation Learning by Graph-Based Consistent Constraints
* Versatile Approach for Solving PnP, PnPf, and PnPfr Problems, A
* Video Summarization with Long Short-Term Memory
* View Synthesis by Appearance Flow
* Visual Motif Discovery via First-Person Vision
* Visual Relationship Detection with Language Priors
* Visualizing Image Priors
* VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction
* Weakly Supervised Learning of Heterogeneous Concepts in Videos
* Weakly Supervised Localization Using Deep Feature Maps
* Weakly Supervised Object Localization Using Size Estimates
* Weakly-Supervised Semantic Segmentation Using Motion Cues
* Webly-Supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames
* What Happens If... Learning to Predict the Effect of Forces in Images
* What's the Point: Semantic Segmentation with Point Supervision
* When is Rotations Averaging Hard?
* Where Should Saliency Models Look Next?
* XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
* Zero-Shot Recognition via Structured Prediction
* Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net
416 for ECCV16

ECCV18 * *ECCV
* 3D Ego-Pose Estimation via Imitation Learning
* 3D Face Reconstruction from Light Field Images: A Model-Free Approach
* 3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation
* 3D Scene Flow from 4D Light Field Gradients
* 3D Vehicle Trajectory Reconstruction in Monocular Video Data Using Environment Structure Constraints
* 3D-CODED: 3D Correspondences by Deep Deformation
* 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
* 3DMV: Joint 3D-Multi-view Prediction for 3D Semantic Scene Segmentation
* A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation
* A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws
* Accelerating Dynamic Programs via Nested Benders Decomposition with Application to Multi-Person Pose Estimation
* Accurate Scene Text Detection Through Border Semantics Awareness and Bootstrapping
* Acquisition of Localization Confidence for Accurate Object Detection
* Action Anticipation with RBF Kernelized Feature Mapping RNN
* Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization
* ActiveStereoNet: End-to-End Self-supervised Learning for Active Stereo Systems
* Actor-Centric Relation Network
* Adaptive Affinity Fields for Semantic Segmentation
* Adaptively Transforming Graph Matching
* Adding Attentiveness to the Neurons in Recurrent Neural Networks
* Adversarial Approach to Hard Triplet Generation, An
* Adversarial Geometry-Aware Human Motion Prediction
* Adversarial Open-World Person Re-Identification
* ADVIO: An Authentic Dataset for Visual-Inertial Odometry
* ADVISE: Symbolism and External Knowledge for Decoding Advertisements
* Affine Correspondences Between Central Cameras for Rapid Relative Pose Estimation
* Affinity Derivation and Graph Merge for Instance Segmentation
* AGIL: Learning Attention from Human for Visuomotor Tasks
* AMC: AutoML for Model Compression and Acceleration on Mobile Devices
* Analyzing Clothing Layer Deformation Statistics of 3D Human Motions
* Appearance-Based Gaze Estimation via Evaluation-Guided Asymmetric Regression
* ArticulatedFusion: Real-Time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera
* Ask, Acquire, and Attack: Data-Free UAP Generation Using Class Impressions
* Associating Inter-image Salient Instances for Weakly Supervised Semantic Segmentation
* Asynchronous, Photometric Feature Tracking Using Events and Frames
* Attend and Rectify: A Gated Attention Mechanism for Fine-Grained Recovery
* Attention-Aware Deep Adversarial Hashing for Cross-Modal Retrieval
* Attention-Based Ensemble for Deep Metric Learning
* Attention-GAN for Object Transfiguration in Wild Images
* Attentive Semantic Alignment with Offset-Aware Correlation Kernels
* Attribute-Guided Face Generation Using Conditional CycleGAN
* Attributes as Operators: Factorizing Unseen Attribute-Object Compositions
* Audio-Visual Event Localization in Unconstrained Videos
* Audio-Visual Scene Analysis with Self-Supervised Multisensory Features
* AugGAN: Cross Domain Adaptation with GAN-Based Data Augmentation
* AutoLoc: Weakly-Supervised Temporal Action Localization in Untrimmed Videos
* Bayesian Semantic Instance Segmentation in Open Set World
* Beyond Local Reasoning for Stereo Confidence Estimation with Deep Learning
* Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)
* Bi-box Regression for Pedestrian Detection and Occlusion Estimation
* Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm
* Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection
* BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation
* BodyNet: Volumetric Inference of 3D Human Body Shapes
* Boosted Attention: Leveraging Human Attention for Image Captioning
* BOP: Benchmark for 6D Object Pose Estimation
* Broadcasting Convolutional Network for Visual Relational Reasoning
* BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
* Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks
* BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization
* C-WSL: Count-Guided Weakly Supervised Localization
* CAR-Net: Clairvoyant Attentive Recurrent Network
* CBAM: Convolutional Block Attention Module
* CGIntrinsics: Better Intrinsic Image Decomposition Through Physically-Based Rendering
* Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation
* Choose Your Neuron: Incorporating Domain Knowledge Through Neuron-Importance
* CIRL: Controllable Imitative Reinforcement Learning for Vision-Based Self-driving
* Closed-Form Solution to Photorealistic Image Stylization, A
* Clustering Convolutional Kernels to Compress Deep Neural Networks
* CNN-PS: CNN-Based Photometric Stereo for General Non-convex Surfaces
* Coded Illumination and Imaging for Fluorescence Based Classification
* Coded Two-Bucket Cameras for Computer Vision
* Collaborative Deep Reinforcement Learning for Multi-object Tracking
* Coloring with Words: Guiding Image Colorization Through Text-Based Palette Generation
* Combining 3D Model Contour Energy and Keypoints for Object Tracking
* Comparator Networks
* Compositing-Aware Image Search
* Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds
* Compositional Learning for Human Object Interaction
* Compound Memory Networks for Few-Shot Video Classification
* Compressing the Input for CNNs with the First-Order Scattering Transform
* Concept Mask: Large-Scale Segmentation from Semantic Concepts
* Conditional Image-Text Embedding Networks
* Conditional Prior Networks for Optical Flow
* Connecting Gaze, Scene, and Attention: Generalized Attention Estimation via Joint Modeling of Gaze and Scene Saliency
* Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition
* Constrained Optimization Based Low-Rank Approximation of Deep Neural Networks
* Constraint-Aware Deep Neural Network Compression
* Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias
* Context Refinement for Object Detection
* Contextual Loss for Image Transformation with Non-aligned Data, The
* Contextual-Based Image Inpainting: Infer, Match, and Translate
* ContextVP: Fully Context-Aware Video Prediction
* Contour Knowledge Transfer for Salient Object Detection
* ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
* Convolutional Networks with Adaptive Inference Graphs
* Coreset-Based Neural Network Compression
* CornerNet: Detecting Objects as Paired Keypoints
* Correcting the Triplet Selection Bias for Triplet Loss
* CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps
* Cross-Modal and Hierarchical Modeling of Video and Text
* Cross-Modal Hamming Hashing
* Cross-Modal Ranking with Soft Consistency and Noisy Labels for Robust RGB-T Tracking
* CrossNet: An End-to-End Reference-Based Super Resolution Network Using Cross-Scale Warping
* CTAP: Complementary Temporal Action Proposal Generation
* CubeNet: Equivariance to 3D Rotation and Translation
* CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
* Data-Driven Sparse Structure Selection for Deep Neural Networks
* Dataset and Architecture for Visual Reasoning with a Working Memory, A
* Dataset for Lane Instance Segmentation in Urban Environments, A
* Dataset of Flash and Ambient Illumination Pairs from the Crowd, A
* DCAN: Dual Channel-Wise Alignment Networks for Unsupervised Scene Adaptation
* DDRNet: Depth Map Denoising and Refinement for Consumer Depth Cameras Using Cascaded CNNs
* Deblurring Natural Image Using Super-Gaussian Fields
* Decouple Learning for Parameterized Image Operators
* Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment
* Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: The Benefit of Target Expectation Maximization
* Deep Attention Neural Tensor Network for Visual Question Answering
* Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling
* Deep Bilevel Learning
* Deep Bilinear Learning for RGB-D Action Recognition
* Deep Boosting for Image Denoising
* Deep Burst Denoising
* Deep Clustering for Unsupervised Learning of Visual Features
* Deep Co-Training for Semi-Supervised Image Recognition
* Deep Component Analysis via Alternating Direction Neural Networks
* Deep Continuous Fusion for Multi-sensor 3D Object Detection
* Deep Cross-Modal Projection Learning for Image-Text Matching
* Deep Cross-Modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-Based 3D Shape Retrieval
* Deep Directional Statistics: Pose Estimation with Uncertainty Quantification
* Deep Discriminative Model for Video Classification
* Deep Domain Generalization via Conditional Invariant Adversarial Networks
* Deep Expander Networks: Efficient Deep Networks from Graph Theory
* Deep Factorised Inverse-Sketching
* Deep Feature Factorization for Concept Discovery
* Deep Feature Pyramid Reconfiguration for Object Detection
* Deep Fundamental Matrix Estimation
* Deep Generative Models for Weakly-Supervised Multi-Label Classification
* Deep High Dynamic Range Imaging with Large Foreground Motions
* Deep Image Demosaicking Using a Cascade of Convolutional Residual Denoising Networks
* Deep Imbalanced Attribute Classification Using Visual Attention Aggregation
* Deep Kalman Filtering Network for Video Compression Artifact Reduction
* Deep Metric Learning with Hierarchical Triplet Loss
* Deep Model-Based 6D Pose Refinement in RGB
* Deep Multi-task Learning to Recognise Subtle Facial Expressions of Mental States
* Deep Pictorial Gaze Estimation
* Deep Randomized Ensembles for Metric Learning
* Deep Recursive HDRI: Inverse Tone Mapping Using Generative Adversarial Networks
* Deep Regionlets for Object Detection
* Deep Regression Tracking with Shrinkage Loss
* Deep Reinforcement Learning with Iterative Shift for Visual Tracking
* Deep Shape Matching
* Deep Structure Inference Network for Facial Action Unit Recognition
* Deep Texture and Structure Aware Filtering Network for Image Smoothing
* Deep Variational Metric Learning
* Deep Video Generation, Prediction and Completion of Human Action Sequences
* Deep Video Quality Assessor: From Spatio-Temporal Visual Sensitivity to a Convolutional Neural Aggregation Network
* Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry
* Deep Volumetric Video from Very Sparse Multi-View Performance Capture
* DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Model
* DeepIM: Deep Iterative Matching for 6D Pose Estimation
* DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
* DeepKSPD: Learning Kernel-Matrix-Based SPD Representation For Fine-Grained Image Recognition
* Deeply Learned Compositional Models for Human Pose Estimation
* Deeply-Initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment, A
* DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks
* DeepTAM: Deep Tracking and Mapping
* DeepVS: A Deep Learning Based Video Saliency Prediction Approach
* DeepWrinkles: Accurate and Realistic Clothing Modeling
* Deformable Pose Traversal Convolution for 3D Action and Gesture Recognition
* Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance
* Dense Pose Transfer
* Dense Semantic and Topological Correspondence of 3D Faces without Landmarks
* Dependency-Aware Attention Control for Unconstrained Face Recognition with Image Sets
* Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network
* Depth-Aware CNN for RGB-D Segmentation
* Descending, Lifting or Smoothing: Secrets of Robust Cost Optimization
* Deterministic Consensus Maximization with Biconvex Programming
* DetNet: Design Backbone for Object Detection
* Devil of Face Recognition Is in the Noise, The
* DF-Net: Unsupervised Joint Learning of Depth and Flow Using Cross-Task Consistency
* DFT-based Transformation Invariant Pooling Layer for Visual Classification
* Diagnosing Error in Temporal Action Detectors
* Direct Sparse Odometry with Rolling Shutter
* Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation
* Disentangling Factors of Variation with Cycle-Consistent Variational Auto-encoders
* Dist-GAN: An Improved GAN Using Distance Constraints
* Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images
* Distractor-Aware Siamese Networks for Visual Object Tracking
* Diverse and Coherent Paragraph Generation from Images
* Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes
* Diverse Feature Visualizations Reveal Invariances in Early Layers of Deep Neural Networks
* Diverse Image-to-Image Translation via Disentangled Representations
* Dividing and Aggregating Network for Multi-view Action Recognition
* DOCK: Detecting Objects by Transferring Common-Sense Knowledge
* Does Haze Removal Help CNN-Based Image Classification?
* Domain Adaptation Through Synthesis for Unsupervised Person Re-identification
* Domain Transfer Through Deep Activation Matching
* Double JPEG Detection in Mixed JPEG Quality Factors Using Deep Convolutional Neural Network
* DPP-Net: Device-Aware Progressive Search for Pareto-Optimal Neural Architectures
* Dual-Agent Deep Reinforcement Learning for Deformable Face Tracking
* DYAN: A Dynamical Atoms-Based Network for Video Prediction
* Dynamic Conditional Networks for Few-Shot Learning
* Dynamic Filtering with Large Sampling Field for ConvNets
* Dynamic Multimodal Instance Segmentation Guided by Natural Language Queries
* Dynamic Task Prioritization for Multitask Learning
* EC-Net: An Edge-Aware Point Set Consolidation Network
* ECO: Efficient Convolutional Network for Online Video Understanding
* Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
* Efficient 6-DoF Tracking of Handheld Objects from an Egocentric Viewpoint
* Efficient Dense Point Cloud Object Reconstruction Using Deformation Vector Fields
* Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search
* Efficient Relative Attribute Learning Using Graph Neural Networks
* Efficient Semantic Scene Completion Network with Spatial Group Convolution
* Efficient Sliding Window Computation for NN-Based Template Matching
* Efficient Uncertainty Estimation for Semantic Segmentation in Videos
* Egocentric Activity Prediction via Event Modulated Attention
* Eigendecomposition-Free Training of Deep Networks with Zero Eigenvalue-Based Losses
* ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
* Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery
* Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
* End-to-End Deep Structured Models for Drawing Crosswalks
* End-to-End Incremental Learning
* End-to-End Joint Semantic Segmentation of Actors and Actions in Video
* End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners
* End-to-End View Synthesis for Light Field Imaging with Pseudo 4DCNN
* Escaping from Collapsing Modes in a Constrained Space
* ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
* Estimating Depth from RGB and Sparse Sensing
* Estimating the Success of Unsupervised Image to Image Translation
* Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane
* ExFuse: Enhancing Feature Fusion for Semantic Segmentation
* Explainable Neural Computation via Stack Neural Module Networks
* ExplainGAN: Model Explanation via Decision Boundary Crossing Transformations
* Exploiting Temporal Information for 3D Human Pose Estimation
* Exploiting Vector Fields for Geometric Rectification of Distorted Document Images
* Exploring the Limits of Weakly Supervised Pretraining
* Exploring Visual Relationship for Image Captioning
* Extending Layered Models to 3D Motion
* Extreme Network Compression via Filter Group Approximation
* Face De-spoofing: Anti-spoofing via Noise Modeling
* Face Recognition with Contrastive Convolution
* Face Super-Resolution Guided by Facial Component Heatmaps
* Faces as Lighting Probes via Unsupervised Deep Highlight Extraction
* Facial Dynamics Interpreter Network: What Are the Important Relations Between Local Dynamics for Facial Trait Estimation?
* Facial Expression Recognition with Inconsistently Annotated Datasets
* Factorizable Net: An Efficient Subgraph-Based Framework for Scene Graph Generation
* Factual or Emotional: Stylized Image Captioning with Adaptive Learning and Attention
* Fast and Accurate Camera Covariance Computation for Large 3D Reconstruction
* Fast and Accurate Intrinsic Symmetry Detection
* Fast Light Field Reconstruction with Deep Coarse-to-Fine Modeling of Spatial-Angular Clues
* Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network
* Few-Shot Human Motion Prediction via Meta-learning
* Fictitious GAN: Training GANs with Historical Models
* Fighting Fake News: Image Splice Detection via Learned Self-Consistency
* Find and Focus: Retrieve and Localize Video Events with Natural Language Queries
* Fine-Grained Video Categorization with Redundancy Reduction Attention
* Fine-Grained Visual Categorization Using Meta-learning Optimization with Sample Selection of Auxiliary Data
* FishEyeRecNet: A Multi-context Collaborative Deep Network for Fisheye Image Rectification
* FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans
* Flow-Grounded Spatial-Temporal Video Prediction from Still Images
* Focus, Segment and Erase: An Efficient Network for Multi-label Brain Tumor Segmentation
* Folded Recurrent Neural Networks for Future Video Prediction
* ForestHash: Semantic Hashing with Shallow Random Forests and Tiny Convolutional Networks
* Framework for Evaluating 6-DOF Object Trackers, A
* From Face Recognition to Models of Identity: A Bayesian Approach to Learning About Unknown Identities from Unsupervised Data
* Fully Motion-Aware Network for Video Object Detection
* Fully-Convolutional Point Networks for Large-Scale Point Clouds
* GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction
* GANimation: Anatomically-Aware Facial Animation from a Single Image
* Generalized Loss-Sensitive Adversarial Learning with Manifold Margins
* Generalizing a Person Retrieval Model Hetero- and Homogeneously
* Generating 3D Faces Using Convolutional Mesh Autoencoders
* Generative Adversarial Network with Spatial Attention for Face Attribute Editing
* Generative Domain-Migration Hashing for Sketch-to-Image Retrieval
* Generative Semantic Manipulation with Mask-Contrasting GAN
* GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
* Geolocation Estimation of Photos Using a Hierarchical Model and Scene Classification
* Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection
* Geometric Perspective on Structured Light Coding, A
* Goal-Oriented Visual Question Generation via Intermediate Rewards
* Good Line Cutting: Towards Accurate Pose Tracking of Line-Assisted VO/VSLAM
* Graininess-Aware Deep Feature Learning for Pedestrian Detection
* Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation
* Graph Distillation for Action Detection with Privileged Modalities
* Graph R-CNN for Scene Graph Generation
* Grassmann Pooling as Compact Homogeneous Bilinear Pooling for Fine-Grained Visual Classification
* Gray-Box Adversarial Training
* GridFace: Face Rectification via Learning Local Homography Transformations
* Grounding Visual Explanations
* Group Normalization
* HairNet: Single-View Hair Reconstruction Using Convolutional Neural Networks
* Hand Pose Estimation via Latent 2.5D Heatmap Regression
* HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision
* Hard-Aware Point-to-Set Deep Metric for Person Re-identification
* Hashing with Binary Matrix Pursuit
* HBE: Hand Branch Ensemble Network for Real-Time 3D Hand Pose Estimation
* HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration
* HiDDeN: Hiding Data With Deep Networks
* Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition
* Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences
* Hierarchical Relational Networks for Group Activity Recognition and Retrieval
* Hierarchy of Alternating Specialists for Scene Recognition
* Highly-Economized Multi-view Binary Compression for Scalable Image Clustering
* Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image
* How Good Is My GAN?
* How Local Is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization
* Human Motion Analysis with Deep Metric Learning
* Hybrid Model for Identity Obfuscation by Face Replacement, A
* HybridFusion: Real-Time Performance Capture Using a Single Depth Sensor and Sparse IMUs
* HybridNet: Classification and Reconstruction Cooperation for Semi-supervised Learning
* ICNet for Real-Time Semantic Segmentation on High-Resolution Images
* Image Generation from Sketch Constraint Using Contextual GAN
* Image Inpainting for Irregular Holes Using Partial Convolutions
* Image Manipulation with Perceptual Discriminators
* Image Reassembly Combining Deep Learning and Shortest Path Problem
* Image Super-Resolution Using Very Deep Residual Channel Attention Networks
* Imagine This! Scripts to Compositions to Videos
* Implicit 3D Orientation Learning for 6D Object Detection from RGB Images
* Improved Structure from Motion Using Fiducial Marker Matching
* Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association
* Improving DNN Robustness to Adversarial Attacks Using Jacobian Regularization
* Improving Generalization via Scalable Neighborhood Component Analysis
* Improving Sequential Determinantal Point Processes for Supervised Video Summarization
* Improving Shape Deformation in Unsupervised Image-to-Image Translation
* Improving Spatiotemporal Self-supervision by Deep Reinforcement Learning
* In the Eye of Beholder: Joint Learning of Gaze and Actions in First Person Video
* Incremental Multi-graph Matching via Diversity and Randomness Based Graph Clustering
* Incremental Non-Rigid Structure-from-Motion with Unknown Focal Length
* Inner Space Preserving Generative Pose Machine
* Instance-Level Human Parsing via Part Grouping Network
* Integral Human Pose Regression
* Integrating Egocentric Videos in Top-View Surveillance Videos: Joint Identification and Temporal Alignment
* Interaction-Aware Spatio-Temporal Pyramid Attention Networks for Action Classification
* Interactive Boundary Prediction for Object Selection
* Interpolating Convolutional Neural Networks Using Batch Normalization
* Interpretable Basis Decomposition for Visual Explanation
* Interpretable Intuitive Physics Model
* Into the Twilight Zone: Depth Estimation Using Joint Structure-Stereo Optimization
* Is Robustness the Cost of Accuracy?: A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
* ISNN: Impact Sound Neural Network for Audio-Visual Object Classification
* Iterative Crowd Counting
* Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
* Joint 3D Tracking of a Deformable Object in Interaction with a Hand
* Joint and Progressive Learning from High-Dimensional Data for Multi-label Classification
* Joint Blind Motion Deblurring and Depth Estimation of Light Field
* Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery
* Joint Learning of Intrinsic Images and Semantic Segmentation
* Joint Map and Symmetry Synchronization
* Joint Optimization for Compressive Video Sensing and Reconstruction Under Hardware Constraints
* Joint Person Segmentation and Identification in Synchronized First- and Third-Person Videos
* Joint Representation and Truncated Inference Learning for Correlation Filter Based Tracking
* Joint Sequence Fusion Model for Video Question Answering and Retrieval, A
* Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation
* Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input
* K-convexity Shape Priors for Segmentation
* Key-Word-Aware Network for Referring Expression Image Segmentation
* Lambda Twist: An Accurate Fast Robust Perspective Three Point (P3P) Solver
* LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction
* Large Scale Urban Scene Modeling from MVS Meshes
* Layer-Structured 3D Scene Inference via View Synthesis
* Learn-to-Score: Efficient 3D Scene Exploration by Predicting View Utility
* Learnable PINs: Cross-modal Embeddings for Person Identity
* Learning 3D Human Pose from Structure and Motion
* Learning 3D Keypoint Descriptors for Non-rigid Shape Matching
* Learning 3D Shapes as Multi-layered Height-Maps Using 2D Convolutional Networks
* Learning and Matching Multi-View Descriptors for Registration of Point Clouds
* Learning Blind Video Temporal Consistency
* Learning Category-Specific Mesh Reconstruction from Image Collections
* Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition
* Learning Compression from Limited Unlabeled Data
* Learning Data Terms for Non-blind Deblurring
* Learning Deep Representations with Probabilistic Knowledge Transfer
* Learning Discriminative Video Representations Using Adversarial Perturbations
* Learning Dynamic Memory Networks for Object Tracking
* Learning Efficient Single-Stage Pedestrian Detectors by Asymptotic Localization Fitting
* Learning Human-Object Interactions by Graph Parsing Neural Networks
* Learning Monocular Depth by Distilling Cross-Domain Stereo Networks
* Learning Priors for Semantic 3D Reconstruction
* Learning Region Features for Object Detection
* Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation
* Learning Shape Priors for Single-View 3D Completion And Reconstruction
* Learning Single-View 3D Reconstruction with Limited Pose Supervision
* Learning SO(3) Equivariant Representations with Spherical CNNs
* Learning to Anonymize Faces for Privacy Preserving Action Detection
* Learning to Blend Photos
* Learning to Capture Light Fields Through a Coded Aperture Camera
* Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World
* Learning to Dodge A Bullet: Concyclic View Morphing via Deep Learning
* Learning to Forecast and Refine Residual Motion for Image-to-Video Generation
* Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching
* Learning to Look around Objects for Top-View Representations of Outdoor Scenes
* Learning to Navigate for Fine-Grained Classification
* Learning to Predict Crisp Boundaries
* Learning to Reconstruct High-Quality 3D Shapes with Cascaded Fully Convolutional Networks
* Learning to Segment via Cut-and-Paste
* Learning to Separate Object Sounds by Watching Unlabeled Video
* Learning to Solve Nonlinear Least Squares for Monocular Stereo
* Learning to Zoom: A Saliency-Based Sampling Layer for Neural Networks
* Learning Type-Aware Embeddings for Fashion Compatibility
* Learning Visual Question Answering by Bootstrapping Hard Attention
* Learning Warped Guidance for Blind Face Restoration
* Learning with Biased Complementary Labels
* Learning-Based Video Motion Magnification
* Less Is More: Picking Informative Frames for Video Captioning
* Leveraging Motion Priors in Videos for Improving Human Segmentation
* License Plate Detection and Recognition in Unconstrained Scenarios
* Lifelong Learning via Progressive Distillation and Retrospection
* Lifting Layers: Analysis and Applications
* Light Structure from Pin Motion: Simple and Accurate Point Light Calibration for Physics-Based Modeling
* Linear RGB-D SLAM for Planar Environments
* Linear Span Network for Object Skeleton Detection
* Lip Movements Generation at a Glance
* Liquid Pouring Monitoring via Rich Sensory Inputs
* Local Orthogonal-Group Testing
* Local Spectral Graph Convolution for Point Set Feature Learning
* Localization Recall Precision (LRP): A New Performance Metric for Object Detection
* Long-Term Tracking in the Wild: A Benchmark
* Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation
* Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss
* LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
* LSQ++: Lower Running Time and Higher Recall in Multi-codebook Quantization
* Macro-Micro Adversarial Network for Human Parsing
* Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation
* Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification
* Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
* MaskConnect: Connectivity Learning by Gradient Descent
* Massively Parallel Video Networks
* Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image
* Maximum Margin Metric Learning over Discriminative Nullspace for Person Re-identification
* Memory Aware Synapses: Learning What (not) to Forget
* Meta-tracker: Fast and Robust Online Adaptation for Visual Object Trackers
* Minimal Closed-Form Solution for Multi-perspective Pose Estimation using Points and Lines, A
* ML-LocNet: Improving Object Localization with Multi-view Learning Network
* Modality Distillation with Multiple Stream Networks for Action Recognition
* Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding
* Model-free Consensus Maximization for Non-Rigid Shapes
* Modeling Varying Camera-IMU Time Offset in Optimization-Based Visual-Inertial Odometry
* Modeling Visual Context Is Key to Augmenting Object Detection Datasets
* Modular Generative Adversarial Networks
* Modulation Module for Multi-task Learning with Applications in Image Retrieval, A
* Monocular Depth Estimation Using Whole Strip Masking and Reliability-Based Refinement
* Monocular Depth Estimation with Affinity, Vertical Pooling, and Label Enhancement
* Motion Feature Network: Fixed Motion Filter for Action Recognition
* Move Forward and Tell: A Progressive Generator of Video Descriptions
* MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models
* MRF Optimization with Separable Convex Prior on Partially Ordered Labels
* MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics
* Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition
* Multi-class Model Fitting by Energy Minimization and Mode-Seeking
* Multi-fiber Networks for Video Recognition
* Multi-modal Cycle-Consistent Generalized Zero-Shot Learning
* Multi-object Tracking with Neural Gating Using Bilinear LSTM
* Multi-scale Context Intertwining for Semantic Segmentation
* Multi-scale Residual Network for Image Super-Resolution
* Multi-scale Spatially-Asymmetric Recalibration for Image Classification
* Multi-Scale Structure-Aware Network for Human Pose Estimation
* Multi-view to Novel View: Synthesizing Novel Views With Self-learned Confidence
* Multimodal Dual Attention Memory for Video Story Question Answering
* Multimodal Image Alignment Through a Multiscale Chain of Neural Networks with Application to Remote Sensing
* Multimodal Unsupervised Image-to-Image Translation
* Multiple-Gaze Geometry: Inferring Novel 3D Locations from Gazes Observed in Monocular Video
* MultiPoseNet: Fast Multi-Person Pose Estimation Using Pose Residual Network
* Multiresolution Tree Networks for 3D Point Cloud Processing
* Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond
* Mutex Watershed: Efficient, Parameter-Free Image Partitioning, The
* Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation
* MVSNet: Depth Inference for Unstructured Multi-view Stereo
* MVTec D2S: Densely Segmented Supermarket Dataset
* NAM: Non-Adversarial Unsupervised Domain Mapping
* NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
* Neural Graph Matching Networks for Fewshot 3D Action Recognition
* Neural Network Encapsulation
* Neural Procedural Reconstruction for Residential Buildings
* Neural Stereoscopic Image Style Transfer
* New Large Scale Dynamic Texture Dataset with Application to ConvNet Understanding, A
* NNEval: Neural Network Based Evaluation Metric for Image Captioning
* Normalized Blind Deconvolution
* Object Detection in Video with Spatiotemporal Sampling Networks
* Object Level Visual Reasoning in Videos
* Object-Centered Image Stitching
* Objects that Sound
* Occlusion-Aware Hand Pose Estimation Using Hierarchical Mixture Density Network
* Occlusion-Aware R-CNN: Detecting Pedestrians in a Crowd
* Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation
* OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas
* On Offline Evaluation of Vision-Based Driving Models
* On Regularized Losses for Weakly-supervised CNN Segmentation
* On the Solvability of Viewing Graphs
* Online Detection of Action Start in Untrimmed, Streaming Videos
* Online Dictionary Learning for Approximate Archetypal Analysis
* Online Multi-Object Tracking with Dual Matching Attention Networks
* Open Set Domain Adaptation by Backpropagation
* Open Set Learning with Counterfactual Images
* Open-World Stereo Video Matching with Deep RNN
* Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition
* Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-Out Classifiers
* Pairwise Body-Part Attention for Recognizing Human-Object Interactions
* Pairwise Confusion for Fine-Grained Visual Classification
* Pairwise Relational Networks for Face Recognition
* Parallel Feature Pyramid Network for Object Detection
* PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence
* Part-Activated Deep Reinforcement Learning for Action Prediction
* Part-Aligned Bilinear Representations for Person Re-identification
* Partial Adversarial Domain Adaptation
* Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
* Person Re-identification with Deep Similarity-Guided Graph Neural Network
* Person Search by Multi-Scale Matching
* Person Search in Videos with One Portrait Through Visual and Temporal Links
* Person Search via a Mask-Guided Two-Stream CNN Model
* PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model
* Perturbation Robust Representations of Topological Persistence Diagrams
* Physical Primitive Decomposition
* Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights
* Pivot Correlational Neural Network for Multimodal Video Categorization
* Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
* PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction
* PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-Modalities
* Point-to-Point Regression PointNet for 3D Hand Pose Estimation
* Polarimetric Three-View Geometry
* Pose Guided Human Video Generation
* Pose Partition Networks for Multi-person Pose Estimation
* Pose Proposal Networks
* Pose-Normalized Image Generation for Person Re-Identification
* PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors
* Practical Black-Box Attacks on Deep Neural Networks Using Efficient Query Mechanisms
* Predicting Future Instance Segmentation by Forecasting Convolutional Features
* Predicting Gaze in Egocentric Video by Learning Task-Dependent Attention Transition
* Probabilistic Video Generation Using Holistic Attribute Control
* Product Quantization Network for Fast Image Retrieval
* Programmable Triangulation Light Curtains
* Progressive Neural Architecture Search
* Progressive Structure from Motion
* Propagating LSTM: 3D Pose Estimation Based on Joint Interdependency
* Proximal Dehaze-Net: A Prior Learning-Based Deep Network for Single Image Dehazing
* Proxy Clouds for Live RGB-D Stream Processing and Consolidation
* PS-FCN: A Flexible Learning Framework for Photometric Stereo
* PSANet: Point-wise Spatial Attention Network for Scene Parsing
* PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene Reconstruction
* Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection
* PyramidBox: A Context-Assisted Single Shot Face Detector
* Quadtree Convolutional Neural Networks
* Quantization Mimic: Towards Very Tiny CNN for Object Detection
* Quantized Densely Connected U-Nets for Efficient Landmark Localization
* Quaternion Convolutional Neural Networks
* Question Type Guided Attention in Visual Question Answering
* Question-Guided Hybrid Convolution for Visual Question Answering
* r2p2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting
* RCAA: Relational Context-Aware Agents for Person Search
* Real-Time Actor-Critic Tracking
* Real-Time Hair Rendering Using Sequential Adversarial Networks
* Real-Time MDNet
* Real-to-Virtual Domain Unification for End-to-End Autonomous Driving
* Realtime Time Synchronized Event-Based Stereo
* Receptive Field Block Net for Accurate and Fast Object Detection
* Recognition in Terra Incognita
* Reconstruction-Based Pairwise Depth Dataset for Depth Image Enhancement Using CNN
* Recovering 3D Planes from a Single Image via Convolutional Neural Networks
* Recovering Accurate 3D Human Pose in the Wild Using IMUs and a Moving Camera
* Recurrent Fusion Network for Image Captioning
* Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining
* Recurrent Tubelet Proposal and Recognition Networks for Action Detection
* Recycle-GAN: Unsupervised Video Retargeting
* ReenactGAN: Learning to Reenact Faces via Boundary Transfer
* RefocusGAN: Scene Refocusing Using a Single Image
* Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification
* Relaxation-Free Deep Hashing via Policy Gradient
* RelocNet: Continuous Metric Learning Relocalisation Using Neural Nets
* Remote Photoplethysmography Correspondence Feature for 3D Mask Face Presentation Attack Detection
* Rendering Portraitures from Monocular Camera and Beyond
* Repeatability Is Not Enough: Learning Affine Regions via Discriminability
* RESOUND: Towards Action Recognition Without Representation Bias
* Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
* Rethinking the Form of Latent States in Image Captioning
* Retrospective Encoders for Video Summarization
* Reverse Attention for Salient Object Detection
* Revisiting Autofocus for Smartphone Cameras
* Revisiting RCNN: On Awakening the Classification Power of Faster RCNN
* Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors
* RIDI: Robust IMU Double Integration
* Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
* Robust Anchor Embedding for Unsupervised Video Person re-IDentification in the Wild
* Robust Fitting in Computer Vision: Easy or Hard?
* Robust Image Stitching with Multiple Registrations
* Robust Optical Flow in Rainy Scenes
* Rolling Shutter Pose and Ego-Motion Estimation Using Shape-from-Template
* RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments
* SaaS: Speed as a Supervisor for Semi-supervised Learning
* Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics
* Saliency Detection in 360° Videos
* Saliency Preservation in Low-Resolution Grayscale Images
* Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground
* Sampling Algebraic Varieties for Robust Camera Autocalibration
* SAN: Learning Relationship Between Convolutional Features for Multi-scale Object Detection
* Scalable Exemplar-Based Subspace Clustering Algorithm for Class-Imbalanced Data, A
* Scale Aggregation Network for Accurate and Efficient Crowd Counting
* Scale-Awareness of Light Field Camera Based Visual Odometry
* Scaling Egocentric Vision: The Epic Kitchens Dataset
* Scenes-Objects-Actions: A Multi-task, Multi-label Video Dataset
* SDC-Net: Video Prediction Using Spatially-Displaced Convolution
* Second-Order Democratic Aggregation
* Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal
* Seeing Tree Structure from Vibration
* Segmentation-Aware Deep Fusion Network for Compressed Sensing MRI, A
* SegStereo: Exploiting Semantic Information for Disparity Estimation
* Selective Zero-Shot Classification with Augmented Attributes
* Self-calibration of Cameras with Euclidean Image Plane in Case of Two Views and Known Relative Rotation Angle
* Self-produced Guidance for Weakly-Supervised Object Localization
* Self-supervised Knowledge Distillation Using Singular Value Decomposition
* Self-Supervised Relative Depth Learning for Urban Scene Understanding
* Selfie Video Stabilization
* Semantic Match Consistency for Long-Term Visual Localization
* Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization
* Semi-convolutional Operators for Instance Segmentation
* Semi-dense 3D Reconstruction with a Stereo Event Camera
* Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model
* Semi-supervised Deep Learning with Memory
* Semi-supervised FusedGAN for Conditional Image Generation
* Semi-supervised Generative Adversarial Hashing for Image Retrieval
* Separating Reflection and Transmission Images in the Wild
* Sequential Clique Optimization for Video Object Segmentation
* Shape Reconstruction Using Volume Sweeping and Learned Photoconsistency
* ShapeCodes: Self-supervised Feature Learning by Lifting Views to Viewgrids
* ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking
* Shift-Net: Image Inpainting via Deep Feature Rearrangement
* Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data
* Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features
* ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
* Sidekick Policy Learning for Active Visual Exploration
* Simple Baselines for Human Pose Estimation and Tracking
* Simultaneous 3D Reconstruction for Water Surface and Underwater Scene
* Simultaneous Edge Alignment and Learning
* Single Image Highlight Removal with a Sparse and Low-Rank Reflection Model
* Single Image Intrinsic Decomposition Without a Single Intrinsic Image
* Single Image Water Hazard Detection Using FCN with Reflection Attention Units
* Single Shot Scene Text Retrieval
* Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
* SketchyScene: Richly-Annotated Scene Sketches
* SkipNet: Learning Dynamic Routing in Convolutional Networks
* Small-Scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation
* Snap Angle Prediction for 360° Panoramas
* SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network
* Sound of Pixels, The
* Sparsely Aggregated Convolutional Networks
* Spatio-temporal Channel Correlation Networks for Action Classification
* Spatio-Temporal Transformer Network for Video Restoration
* Specular-to-Diffuse Translation for Multi-view Reconstruction
* SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images
* SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
* SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain Adaptation
* SRFeat: Single Image Super-Resolution with Feature Discrimination
* Stacked Cross Attention for Image-Text Matching
* stagNet: An Attentive Semantic RNN for Group Activity Recognition
* StarMap for Category-Agnostic Keypoint and Viewpoint Estimation
* Start, Follow, Read: End-to-End Full-Page Handwriting Recognition
* Statistically-Motivated Second-Order Pooling
* Stereo Computation for a Single Mixture Image
* Stereo Relative Pose from Line and Point Feature Triplets
* Stereo Vision-Based Semantic 3D Object and Ego-Motion Tracking for Autonomous Driving
* StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction
* Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering
* Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields
* Structural Consistency and Controllability for Diverse Colorization
* Structure-from-Motion-Aware PatchMatch for Adaptive Optical Flow Estimation
* Structured Siamese Network for Real-Time Visual Tracking
* Style-Aware Content Loss for Real-Time HD Style Transfer, A
* Sub-GAN: An Unsupervised Generative Model via Subspaces
* Summarizing First-Person Videos from Third Persons' Points of Views
* Super-Identity Convolutional Neural Network for Face Hallucination
* Super-Resolution and Sparse View CT Reconstruction
* Superpixel Sampling Networks
* Supervising the New with the Old: Learning SFM from SFM
* SwapNet: Image Based Garment Transfer
* Switchable Temporal Propagation Network
* Synthetically Supervised Feature Learning for Scene Text Recognition
* Systematic DNN Weight Pruning Framework Using Alternating Direction Method of Multipliers, A
* T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks
* Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset
* Task-Aware Image Downscaling
* Task-Driven Webpage Saliency
* TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights
* Teaching Machines to Understand Baseball Games: Large-Scale Baseball Video Database for Multiple Video Understanding Tasks
* Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos
* Temporal Relational Reasoning in Videos
* TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
* Textual Explanations for Self-Driving Vehicles
* To Learn Image Super-Resolution, Use a GAN to Learn How to Do Image Degradation First
* Toward Characteristic-Preserving Image-Based Virtual Try-On Network
* Toward Scale-Invariance and Position-Sensitive Region Proposal Networks
* Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline
* Towards Human-Level License Plate Recognition
* Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
* Towards Realistic Predictors
* Towards Robust Neural Networks via Random Self-Ensemble
* Tracking Emerges by Colorizing Videos
* TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
* Training Binary Weight Networks via Semi-Binary Decomposition
* Transductive Centroid Projection for Semi-supervised Large-Scale Recognition
* Transductive Semi-Supervised Deep Learning Using Min-Max Features
* Transferable Adversarial Perturbations
* Transferring GANs: Generating Images from Limited Data
* Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising, A
* Triplet Loss in Siamese Network for Object Tracking
* TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection
* Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
* U-PC: Unsupervised Planogram Compliance
* Uncertainty Estimates and Multi-hypotheses Networks for Optical Flow
* Understanding Degeneracies and Ambiguities in Attribute Transfer
* Understanding Perceptual and Conceptual Fluency at a Large Scale
* Unified Framework for Multi-view Multi-class Object Pose Estimation, A
* Unified Perceptual Parsing for Scene Understanding
* Universal Sketch Perceptual Grouping
* Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking, The
* Unpaired Image Captioning by Language Pivoting
* Unsupervised Class-Specific Deblurring
* Unsupervised CNN-Based Co-saliency Detection with Graphical Optimization
* Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency
* Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training
* Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation
* Unsupervised Hard Example Mining from Videos for Improved Object Detection
* Unsupervised Holistic Image Generation from Key Local Patches
* Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks
* Unsupervised Learning of Multi-Frame Optical Flow with Occlusions
* Unsupervised Person Re-identification by Deep Learning Tracklet Association
* Unsupervised Video Object Segmentation Using Motion Saliency-Guided Spatio-Temporal Propagation
* Unsupervised Video Object Segmentation with Motion-Based Bilateral Networks
* Unveiling the Power of Deep Tracking
* Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data
* Using LIP to Gloss Over Faces in Single-Stage Face Detection Networks
* Using Object Information for Spotting Text
* Value-Aware Quantization for Training and Inference of Neural Networks
* Variable Ring Light Imaging: Capturing Transient Subsurface Scattering with an Ordinary Camera
* Variational Wasserstein Clustering
* Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes
* Video Compression Through Image Interpolation
* Video Object Detection with an Aligned Spatial-Temporal Memory
* Video Object Segmentation by Learning Location-Sensitive Embeddings
* Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation
* Video Re-localization
* Video Summarization Using Fully Convolutional Sequence Networks
* VideoMatch: Matching Based Video Object Segmentation
* Videos as Space-Time Region Graphs
* View-Graph Selection Framework for SfM
* Viewpoint Estimation: Insights and Model
* Visual Coreference Resolution in Visual Dialog Using Neural Module Networks
* Visual Psychophysics for Making Face Recognition Algorithms More Explainable
* Visual Question Answering as a Meta Learning Task
* Visual Question Generation for Class Acquisition of Unknown Objects
* Visual Reasoning with Multi-hop Feature Modulation
* Visual Text Correction
* Visual Tracking via Spatially Aligned Correlation Filters Network
* Visual-Inertial Object Detection and Mapping
* Volumetric Performance Capture from Minimal Camera Viewpoints
* VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions
* VSO: Visual Semantic Odometry
* W-TALC: Weakly-Supervised Temporal Activity Localization and Classification
* Wasserstein Divergence for GANs
* Weakly Supervised Region Proposal Network and Object Detection
* Weakly- and Semi-supervised Panoptic Segmentation
* Weakly-Supervised 3D Hand Pose Estimation from Monocular RGB Images
* Weakly-Supervised Video Summarization Using Variational Encoder-Decoder and Web Prior
* What Do I Annotate Next? An Empirical Study of Active Learning for Action Localization
* Where Are the Blobs: Counting by Localization with Point Supervision
* Where Will They Go? Predicting Fine-Grained Adversarial Multi-agent Motion Using Conditional Variational Autoencoders
* WildDash: Creating Hazard-Aware Benchmarks
* Women Also Snowboard: Overcoming Bias in Captioning Models
* X-Ray Computed Tomography Through Scatter
* X2Face: A Network for Controlling Face Generation Using Images, Audio, and Pose Codes
* YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
* Zero-Annotation Object Detection with Web Knowledge Transfer
* Zero-Shot Deep Domain Adaptation
* Zero-Shot Framework for Sketch Based Image Retrieval, A
* Zero-Shot Keyword Spotting for Visual Speech Recognition In-the-wild
* Zero-Shot Object Detection
* Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition
776 for ECCV18

ECCV20 * *ECCV
* 360° Camera Alignment via Segmentation
* 3d Bird Reconstruction: A Dataset, Model, and Shape Recovery from a Single View
* 3d Fluid Flow Reconstruction Using Compact Light Field PIV
* 3d Human Shape and Pose from a Single Low-resolution Image with Self-supervised Learning
* 3d Human Shape Reconstruction from a Polarization Image
* 3d Scene Reconstruction from a Single Viewport
* 3D-CVF: Generating Joint Camera and Lidar Features Using Cross-view Spatial Feature Fusion for 3D Object Detection
* 3D-Rotation-Equivariant Quaternion Neural Networks
* 3PointTM: Faster Measurement of High-dimensional Transmission Matrices
* 6d Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference
* AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling
* Accelerating CNN Training by Pruning Activation Gradients
* Accelerating Deep Learning with Millions of Classes
* Accurate Optimization of Weighted Nuclear Norm for Non-rigid Structure from Motion
* Accurate Polarimetric BRDF for Real Polarization Scene Rendering
* Accurate Reconstruction of Oriented 3d Points Using Affine Correspondences
* Accurate Rgb-d Salient Object Detection via Collaborative Learning
* Acquiring Dynamic Light Fields Through Coded Aperture Camera
* Across Scales and Across Dimensions: Temporal Super-Resolution Using Deep Internal Learning
* Action Localization Through Continual Predictive Learning
* Actions as Moving Points
* Active Crowd Counting with Limited Supervision
* Active Perception Using Light Curtains for Autonomous Driving
* Active Visual Information Gathering for Vision-language Navigation
* Adapting Object Detectors with Conditional Domain Normalization
* Adaptive Computationally Efficient Network for Monocular 3d Hand Pose Estimation
* Adaptive Margin Diversity Regularizer for Handling Data Imbalance in Zero-Shot SBIR
* Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting
* Adaptive Object Detection with Dual Multi-label Prediction
* Adaptive Offline Quintuplet Loss for Image-text Matching
* Adaptive Task Sampling for Meta-learning
* Adaptive Text Recognition Through Visual Matching
* Adaptive Variance Based Label Distribution Learning for Facial Age Estimation
* Adaptive Video Highlight Detection by Learning from User History
* Adversarial Background-aware Loss for Weakly-supervised Temporal Activity Localization
* Adversarial Data Augmentation via Deformation Statistics
* Adversarial Generative Grammars for Human Activity Prediction
* Adversarial Learning for Zero-shot Domain Adaptation
* Adversarial Ranking Attack and Defense
* Adversarial Robustness on In- and Out-distribution Improves Explainability
* Adversarial Self-supervised Learning for Semi-Supervised 3d Action Recognition
* Adversarial Semantic Data Augmentation for Human Pose Estimation
* Adversarial T-shirt! Evading Person Detectors in a Physical World
* Adversarial Training with Bi-Directional Likelihood Regularization for Visual Classification
* Advpc: Transferable Adversarial Perturbations on 3d Point Clouds
* Ae Textspotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
* AE-OT-GAN: Training GANs from Data Specific Latent Distribution
* AiR: Attention with Reasoning Capability
* Aligning Videos in Space and Time
* All at Once: Temporally Adaptive Multi-frame Interpolation with Advanced Motion Modeling
* ALRe: Outlier Detection for Guided Refinement
* Amln: Adversarial-based Mutual Learning Network for Online Knowledge Distillation
* Amplifying Key Cues for Human-object-interaction Detection
* Analysis of Sketched IRLS for Accelerated Sparse Residual Regression, An
* Anatomy-aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images
* Angle-based Search Space Shrinking for Neural Architecture Search
* Anti-Bandit Neural Architecture Search for Model Defense
* API-net: Robust Generative Classifier via a Single Discriminator
* Appearance Consensus Driven Self-supervised Human Mesh Recovery
* Appearance-preserving 3d Convolution for Video-based Person Re-identification
* Apricot: A Dataset of Physical Adversarial Attacks on Object Detection
* Ar-net: Adaptive Frame Resolution for Efficient Action Recognition
* Arbitrary-Oriented Object Detection with Circular Smooth Label
* Are Labels Necessary for Neural Architecture Search?
* Assemblenet++: Assembling Modality Representations via Attention Connections
* Associative Alignment for Few-shot Image Classification
* Associative3d: Volumetric Reconstruction from Sparse Views
* Asymmetric Modeling for Action Assessment, An
* Asymmetric Two-stream Architecture for Accurate RGB-D Saliency Detection
* Asynchronous Interaction Aggregation for Action Detection
* Atlantanet: Inferring the 3d Indoor Layout from a Single 360° Image Beyond the Manhattan World Assumption
* Atlas: End-to-end 3d Scene Reconstruction from Posed Images
* Attend and Segment: Attention Guided Active Semantic Segmentation
* Attention Guided Anomaly Localization in Images
* Attention-based Query Expansion Learning
* Attention-driven Dynamic Graph Convolutional Network for Multi-label Image Recognition
* Attention-driven Two-stage Clustering Method for Unsupervised Person Re-identification, An
* Attentionnas: Spatiotemporal Attention Cell Search for Video Classification
* Attentive Normalization
* Attentive Prototype Few-shot Learning with Capsule Network-based Embedding
* Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation
* Attributional Robustness Training Using Input-gradient Spatial Alignment
* Auto3d: Novel View Synthesis Through Unsupervisely Learned Variational Viewpoint and Global 3d Representation
* Autoencoder-based Graph Construction for Semi-supervised Learning
* AutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter Learning
* Autoregressive Unsupervised Image Segmentation
* Autosimulate: (quickly) Learning Synthetic Data Generation
* Autostr: Efficient Backbone Search for Scene Text Recognition
* Autotrajectory: Label-free Trajectory Extraction and Prediction from Videos Using Dynamic Points
* Average Mixing Kernel Signature, The
* Axial-Deeplab: Stand-alone Axial-Attention for Panoptic Segmentation
* Backpropagated Gradient Representations for Anomaly Detection
* Balanced and Uncertainty-aware Approach for Partial Domain Adaptation, A
* Bats: Binary Architecture Search
* BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network
* Bcnet: Learning Body and Cloth Shape from a Single Image
* Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-language Models
* Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction
* Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes
* Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
* Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding
* Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments
* Bi-directional Cross-modality Feature Propagation with Separation-and-aggregation Gate for RGB-D Semantic Segmentation
* Bias-based Universal Adversarial Patch Attack for Automatic Check-out
* Big Transfer (BIT): General Visual Representation Learning
* Bignas: Scaling up Neural Architecture Search with Big Single-stage Models
* Binarized Neural Network for Single Image Super Resolution
* Biometricnet: Deep Unconstrained Face Verification Through Learning of Metrics Regularized onto Gaussian Distributions
* Birnat: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging
* Blended Grammar Network for Human Parsing
* Blind Face Restoration via Deep Multi-scale Component Dictionaries
* BLSM: A Bone-level Skinned Model of the Human Mesh
* BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation
* Boosting Decision-based Black-box Adversarial Attacks with Random Sign Flip
* Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer
* BorderDet: Border Feature for Dense Object Detection
* Bottom-up Temporal Action Localization with Mutual Regularization
* Boundary Based Out-of-Distribution Classifier for Generalized Zero-shot Learning, A
* Boundary Content Graph Neural Network for Temporal Action Proposal Generation
* Boundary-aware Cascade Networks for Temporal Action Segmentation
* Boundary-preserving Mask R-CNN
* Bounding-box Channels for Visual Relationship Detection
* Box2seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised Segmentation
* Bridging Knowledge Graphs to Generate Scene Graphs
* Broader Study of Cross-domain Few-shot Learning, A
* Broadface: Looking at Tens of Thousands of People at once for Face Recognition
* BSL-1K: Scaling Up Co-articulated Sign Language Recognition Using Mouthing Cues
* Burst Denoising via Temporally Shifted Wavelet Transforms
* Byeglassesgan: Identity Preserving Eyeglasses Removal for Face Images
* BézierSketch: A Generative Model for Scalable Vector Sketches
* CAD-deform: Deformable Fitting of CAD Models to 3D Scans
* Cafe-GAN: Arbitrary Face Attribute Editing with Complementary Attention Feature
* Calibration-free Structure-from-motion with Calibrated Radial Trifocal Tensors
* Can You Read Me Now? Content Aware Rectification Using Angle Supervision
* Caption-supervised Face Recognition: Training a State-of-the-Art Face Model Without Manual Annotation
* Captioning Images Taken by People Who Are Blind
* Cascade Graph Neural Networks for RGB-D Salient Object Detection
* Catch: Context-based Meta Reinforcement Learning for Transferrable Architecture Search
* Category Level Object Pose Estimation via Neural Analysis-by-Synthesis
* Celeba-Spoof: Large-scale Face Anti-spoofing Dataset with Rich Annotations
* Centernet Heatmap Propagation for Real-time Video Object Detection
* CFAD: Coarse-to-fine Action Detector for Spatiotemporal Action Localization
* Chained-tracker: Chaining Paired Attentive Regression Results for End-to-end Joint Multiple-object Detection and Tracking
* Challenge-aware RGBT Tracking
* Channel Selection Using Gumbel Softmax
* Character Grounding and Re-identification in Story of Videos and Text Descriptions
* Character Region Attention for Text Spotting
* Character-preserving Coherent Story Visualization
* Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection
* Circumventing Outliers of Autoaugment with Knowledge Distillation
* Class-incremental Domain Adaptation
* Class-wise Dynamic Graph Convolution for Semantic Segmentation
* Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
* Claws: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection
* Cliffnet for Monocular Depth Estimation with Hierarchical Embedding Loss
* Clnet: A Compact Latent Network for Fast Adjusting Siamese Trackers
* Closer Look at Generalisation in RAVEN, A
* Closer Look at Local Aggregation Operators in Point Cloud Analysis, A
* Closest Point Proposal for MCMC-based Probabilistic Surface Registration, A
* Cloth3D: Clothed 3D Humans
* Clustering Driven Deep Autoencoder for Video Anomaly Detection
* CN: Channel Normalization for Point Cloud Recognition
* Co-heterogeneous and Adaptive Segmentation from Multi-source and Multi-phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation
* Coco-funit: Few-shot Unsupervised Image Translation with a Content Conditioned Style Encoder
* Collaboration by Competition: Self-coordinated Knowledge Amalgamation for Multi-Talent Student Learning
* Collaborative Learning of Gesture Recognition and 3d Hand Pose Estimation with Multi-order Feature Analysis
* Collaborative Training Between Region Proposal Localization and Classification for Domain Adaptive Object Detection
* Collaborative Video Object Segmentation by Foreground-background Integration
* Colorization of Depth Map via Disentanglement
* Combining Implicit Function Learning and Parametric Models for 3d Human Reconstruction
* Combining Task Predictors via Enhancing Joint Predictability
* Commonality-parsing Network Across Shape and Appearance for Partially Supervised Instance Segmentation
* Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets
* Competence-aware Curriculum for Visual Concepts Learning via Question Answering, A
* Component Divide-and-conquer for Real-world Image Super-resolution
* Comprehensive Image Captioning via Scene Graph Decomposition
* Comprehensive Study of Weight Sharing in Graph Networks for 3d Human Pose Estimation, A
* Conditional Convolutions for Instance Segmentation
* Conditional Entropy Coding for Efficient Video Compression
* Conditional Image Repainting via Semantic Bridge and Piecewise Value Function
* Conditional Sequential Modulation for Efficient Global Image Retouching
* ConFIG: Controllable Neural Face Image Generation
* Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency
* Connecting Vision and Language with Localized Narratives
* Consensus-aware Visual-semantic Embedding for Image-Text Matching
* Consistency Guided Scene Flow Estimation
* Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost
* Consistently Fast and Globally Optimal Solution to the Perspective-n-point Problem, A
* Contact and Human Dynamics from Monocular Video
* Contactpose: A Dataset of Grasps with Object Contact and Hand Pose
* Content Adaptive and Error Propagation Aware Deep Video Compression
* Content-aware Unsupervised Deep Homography Estimation
* Content-consistent Matching for Domain Adaptive Semantic Segmentation
* Context-aware RCNN: A Baseline for Action Detection in Videos
* Context-gated Convolution
* Contextual Diversity for Active Learning
* Contextual Heterogeneous Graph Network for Human-object Interaction Detection
* Contextual-relation Consistent Domain Adaptation for Semantic Segmentation
* Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections
* Contrastive Learning for Unpaired Image-to-image Translation
* Contrastive Learning for Weakly Supervised Phrase Grounding
* Contrastive Multiview Coding
* Controllable Image Synthesis via SegVAE
* Controlling Style and Semantics in Weakly-supervised Image Generation
* Convolutional Occupancy Networks
* COOGAN: A Memory-efficient Framework for High-resolution Facial Attribute Editing
* Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks, A
* Corenet: Coherent 3d Scene Reconstruction from a Single RGB Image
* Corner Proposal Network for Anchor-free, Two-stage Object Detection
* CosyPose: Consistent Multi-view Multi-object 6d Pose Estimation
* CoTeRe-net: Discovering Collaborative Ternary Relations in Videos
* Count- and Similarity-aware R-CNN for Pedestrian Detection
* Counterfactual Vision-and-Language Navigation via Adversarial Path Sampler
* Coupling Explicit and Implicit Surface Representations for Generative 3d Modeling
* Cpgan: Content-parsing Generative Adversarial Networks for Text-to-image Synthesis
* Cross-attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-resolution
* Cross-domain Cascaded Deep Translation
* Cross-identity Motion Transfer for Arbitrary Objects Through Pose-Attentive Video Reassembling
* Cross-modal Weighting Network for RGB-D Salient Object Detection
* Cross-task Transfer for Geotagged Audiovisual Aerial Scene Recognition
* Crowdsampling the Plenoptic Function
* CSCL: Critical Semantic-consistent Learning for Unsupervised Domain Adaptation
* Curriculum DeepSDF
* Curriculum Manager for Source Selection in Multi-source Domain Adaptation
* Curvelane-NAS: Unifying Lane-sensitive Architecture Search and Adaptive Point Blending
* CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions
* Cyclic Functional Mapping: Self-supervised Correspondence Between Non-isometric Deformable Shapes
* DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search
* Da4ad: End-to-end Deep Attention-based Visual Localization for Autonomous Driving
* DanbooRegion: An Illustration Region Dataset
* Datamix: Efficient Privacy-preserving Edge-cloud Inference
* DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks
* Ddgcn: A Dynamic Directed Graph Convolutional Network for Action Recognition
* Decoupled Learning Scheme for Real-world Burst Denoising from Raw Images, A
* Decoupling GCN with Dropgraph Module for Skeleton-based Action Recognition
* Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images
* Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification
* Deep Cross-species Feature Learning for Animal Face Recognition via Residual Interspecies Equivariant Network
* Deep Decomposition Learning for Inverse Imaging Problems
* Deep Fashion3d: A Dataset and Benchmark for 3d Garment Reconstruction from Single Images
* Deep Feedback Inverse Problem Solver
* Deep Fusionnet for Point Cloud Semantic Segmentation
* Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
* Deep Hashing with Active Pairwise Supervision
* Deep Hough Transform for Semantic Line Detection
* Deep Hough-transform Line Priors
* Deep Image Clustering with Category-style Representation
* Deep Image Compression Using Decoder Side Information
* Deep Learning-based Pupil Center Detection for Fast and Accurate Eye Tracking System
* Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
* Deep Multi Depth Panoramas for View Synthesis
* Deep Near-light Photometric Stereo for Spatially Varying Reflectances
* Deep Novel View Synthesis from Colored 3d Point Clouds
* Deep Plastic Surgery: Robust and Controllable Image Editing with Human-drawn Sketches
* Deep Positional and Relational Feature Learning for Rotation-invariant Point Cloud Analysis
* Deep Reflectance Volumes: Relightable Reconstructions from Multi-view Photometric Images
* Deep Reinforced Attention Learning for Quality-Aware Visual Recognition
* Deep Shape from Polarization
* Deep Space-time Video Upsampling Networks
* Deep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Apertures
* Deep Spiking Neural Network: Energy Efficiency Through Time Based Coding
* Deep Surface Normal Estimation on the 2-sphere with Confidence Guided Semantic Attention
* Deep Transferring Quantization
* Deep Vectorization of Technical Drawings
* Deepfit: 3d Surface Fitting via Neural Network Weighted Least Squares
* DeepGMR: Learning Latent Gaussian Mixture Models for Registration
* Deephandmesh: A Weakly-supervised Deep Encoder-decoder Framework for High-fidelity Hand Mesh Modeling
* DeepLandscape: Adversarial Modeling of Landscape Videos
* DeepSFM: Structure from Motion via Deep Bundle Adjustment
* Defense Against Adversarial Attacks via Controlling Gradient Leaking on Embedded Manifolds
* Defocus Blur Detection via Depth Distillation
* Defocus Deblurring Using Dual-pixel Data
* Deformable Style Transfer
* Deformation-aware 3d Model Embedding and Retrieval
* Deltas: Depth Estimation by Learning Triangulation and Densification of Sparse Points
* Demea: Deep Mesh Autoencoders for Non-rigidly Deforming Objects
* Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
* Dense Reppoints: Representing Visual Objects with Dense Point Sets
* Describing Textures Using Natural Language
* Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents
* Design and Interpretation of Universal Adversarial Patches in Face Detection
* Detail Preserved Point Cloud Completion via Separated Feature Aggregation
* Detecting Human-object Interactions with Action Co-occurrence Priors
* Detecting Natural Disasters, Damage, and Incidents in the Wild
* Determining the Relevance of Features for Deep Neural Networks
* Devil Is in Classification: A Simple Framework for Long-tail Instance Segmentation, The
* Devil Is in the Details: Self-supervised Attention for Vehicle Re-identification, The
* DH3D: Deep Hierarchical 3d Descriptors for Robust Large-scale 6DOF Relocalization
* DHP: Differentiable Meta Pruning via Hypernetworks
* Differentiable Automatic Data Augmentation
* Differentiable Feature Aggregation Search for Knowledge Distillation
* Differentiable Hierarchical Graph Grouping for Multi-person Pose Estimation
* Differentiable Joint Pruning and Quantization for Hardware Efficiency
* Differentiable Programming for Hyperspectral Unmixing Using a Physics-based Dispersion Model
* Differentiable Recurrent Surface for Asynchronous Event-based Data, A
* Diffraction Line Imaging
* Directional Temporal Modeling for Action Recognition
* Disambiguating Monocular Depth Estimation with a Single Transient
* Discrete Point Flow Networks for Efficient Point Cloud Generation
* Discriminability Distillation in Group Representation Learning
* Discriminative Partial Domain Adversarial Network
* Disentangled Non-local Neural Networks
* Disentangling Multiple Features in Video Sequences Using Gaussian Processes in Variational Autoencoders
* Distance-normalized Unified Representation for Monocular 3d Object Detection
* Distribution-balanced Loss for Multi-label Classification in Long-tailed Datasets
* Diva: Diverse Visual Feature Aggregation for Deep Metric Learning
* Dive Deeper into Box for Object Detection
* Diverse and Admissible Trajectory Forecasting Through Multimodal Context Understanding
* DLOW: Diversifying Latent Flows for Diverse Human Motion Prediction
* Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
* Do Not Mask What You Do Not Need to Mask: A Parser-free Virtual Try-on
* Document Structure Extraction Using Prior Based High Resolution Hierarchical Semantic Segmentation
* Domain Adaptation Through Task Distillation
* Domain Adaptive Object Detection via Asymmetric Tri-Way Faster-RCNN
* Domain Adaptive Semantic Segmentation Using Weak Labels
* Domain-invariant Stereo Matching Networks
* Domain-specific Mappings for Generative Adversarial Style Transfer
* Domain2vec: Domain Embedding for Unsupervised Domain Adaptation
* DOPE: Distillation of Part Experts for Whole-body 3d Pose Estimation in the Wild
* DPDist: Comparing Point Clouds Using Deep Point Cloud Distance
* DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction
* DRG: Dual Relation Graph for Human-object Interaction Detection
* DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation
* Dsdnet: Deep Structured Self-driving Network
* Dtvnet: Dynamic Time-lapse Video Generation via Single Still Image
* Du2net: Learning Depth Estimation from Dual-cameras and Dual-pixels
* Dual Adversarial Network for Deep Active Learning
* Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation
* Dual Grid Net: Hand Mesh Vertex Regression from Single Depth Maps
* Dual Mixup Regularized Learning for Adversarial Domain Adaptation
* Dual Refinement Underwater Object Detection Network
* Duality Diagram Similarity: A Generic Framework for Initialization Selection in Task Transfer Learning
* DVI: Depth Guided Video Inpainting for Autonomous Driving
* Dynamic and Static Context-aware Lstm for Multi-agent Motion Prediction
* Dynamic Dual-attentive Aggregation Learning for Visible-infrared Person Re-identification
* Dynamic Group Convolution for Accelerating Convolutional Neural Networks
* Dynamic Low-light Imaging with Quanta Image Sensors
* Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training
* Dynamic ReLU
* Eagleeye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
* Early Exit or Not: Resource-efficient Blind Quality Enhancement for Compressed Images
* Edge-aware Graph Representation Learning and Reasoning for Face Parsing
* Efficient Adversarial Attacks for Visual Object Tracking
* Efficient Attention Mechanism for Visual Dialog that Can Handle All the Interactions Between Multiple Inputs
* Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions
* Efficient Non-line-of-sight Imaging from Transient Sinograms
* Efficient Outdoor 3d Point Cloud Semantic Segmentation for Critical Road Objects and Distributed Contexts
* Efficient Residue Number System Based Winograd Convolution
* Efficient Scale-Permuted Backbone with Learned Resource Distribution
* Efficient Semantic Video Segmentation with Per-frame Inference
* Efficient Spatio-temporal Recurrent Neural Network for Video Deblurring
* Efficient Training Framework for Reversible Neural Architectures, An
* Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight
* Efficientfcn: Holistically-guided Decoding for Semantic Segmentation
* EGDCL: An Adaptive Curriculum Learning Framework for Unbiased Glaucoma Diagnosis
* Embedding Propagation: Smoother Manifold for Few-shot Classification
* Employing Multi-estimations for Weakly-supervised Semantic Segmentation
* Empowering Relational Network by Self-attention Augmented Conditional Random Fields for Group Activity Recognition
* Enabling Deep Residual Networks for Weakly Supervised Object Detection
* Encoding Structure-texture Relation with P-net for Anomaly Detection in Retinal Images
* End-to-end Dynamic Matching Network for Multi-view Multi-person 3d Pose Estimation
* End-to-end Interpretable Learning of Non-blind Image Deblurring
* End-to-end Low Cost Compressive Spectral Imaging with Spatial-spectral Self-attention
* End-to-end Object Detection with Transformers
* End-to-end OCR Text Re-organization Sequence Learning for Rich-text Detail Image Comprehension, An
* End-to-end Trainable Deep Active Contour Models for Automated Image Segmentation: Delineating Buildings in Aerial Imagery
* Energy-based Models for Deep Probabilistic Regression
* Enhanced Sparse Model for Blind Deblurring
* Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning, An
* Entropy Minimisation Framework for Event-based Vision Model Estimation
* Environment-Agnostic Multitask Learning for Natural Language Grounded Navigation
* EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection
* Erasing Appearance Preservation in Optimization-based Smoothing
* Estimating People Flows to Better Count Them in Crowded Scenes
* ETH-Xgaze: A Large Scale Dataset for Gaze Estimation Under Extreme Head Pose and Gaze Variation
* Event Enhanced High-quality Image Recovery
* Event-based Asynchronous Sparse Convolutional Networks
* Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector
* Example-guided Image Synthesis Using Masked Spatial-channel Attention and Self-supervision
* Exchangeable Deep Neural Networks for Set-to-set Matching and Learning
* Exchnet: A Unified Hashing Network for Large-scale Fine-grained Image Retrieval
* Exclusivity-Consistency Regularized Knowledge Distillation for Face Recognition
* Explainable Face Recognition
* Explaining Image Classifiers Using Statistical Fault Localization
* Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks
* Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
* Exploiting Temporal Coherence for Self-supervised One-shot Video Re-identification
* Expressive Telepresence via Modular Codec Avatars
* Extending and Analyzing Self-supervised Learning Across Domains
* Extract and Merge: Superpixel Segmentation with Regional Attributes
* Eyeglasses 3d Shape Reconstruction from a Single Face Image
* Face Anti-spoofing via Disentangled Representation Learning
* Face Anti-spoofing with Human Material Perception
* Face Super-resolution Guided by 3d Facial Priors
* Fair Darts: Eliminating Unfair Advantages in Differentiable Architecture Search
* FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret
* Fairness by Learning Orthogonal Disentangled Representations
* Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards
* Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
* Fast Adaptation to Super-resolution Networks via Meta-learning
* Fast Bi-layer Neural Synthesis of One-shot Realistic Head Avatars
* Fast Video Object Segmentation Using the Global Context Module
* Faster Autoaugment: Learning Augmentation Strategies Using Backpropagation
* Faster Person Re-identification
* Featmatch: Feature-based Augmentation for Semi-supervised Learning
* Feature Normalized Knowledge Distillation for Image Classification
* Feature Pyramid Transformer
* Feature Representation Matters: End-to-end Learning for Reference-based Image Super-resolution
* Feature Space Augmentation for Long-tailed Data
* Feature-metric Loss for Self-supervised Learning of Depth and Egomotion
* Federated Visual Classification with Real-World Data Distribution
* Few-shot Action Recognition with Permutation-invariant Attention
* Few-shot Compositional Font Generation with Dual Memory
* Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild
* Few-shot Scene-adaptive Anomaly Detection
* Few-shot Semantic Segmentation with Democratic Attention Networks
* Few-shot Single-view 3-d Object Reconstruction with Compositional Priors
* Fhde2net: Full High Definition Demoireing Network
* Filter Style Transfer Between Photos
* Finding It at Another Side: A Viewpoint-adapted Matching Encoder for Change Captioning
* Finding Non-uniform Quantization Schemes Using Multi-task Gaussian Processes
* Finding Your (3D) Center: 3d Object Detection Using a Learned Loss
* Fine-grained Visual Classification via Progressive Multi-granularity Training of Jigsaw Patches
* Fixing Localization Errors to Improve Image Classification
* Flexible Recurrent Residual Pyramid Network for Video Frame Interpolation, A
* Flot: Scene Flow on Point Clouds Guided by Optimal Transport
* Flow-edge Guided Video Completion
* Foley Music: Learning to Generate Music from Videos
* Forecasting Human-object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video
* Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-output Observations
* Forkgan: Seeing into the Rainy Night
* Free View Synthesis
* Freecam3d: Snapshot Structured Light 3d with Freely-moving Cameras
* From Image to Stability: Learning Dynamics from Human Pose
* From Shadow Segmentation to Shadow Removal
* FTL: A Universal Framework for Training Low-bit DNNs via Feature Transfer
* Full-body Awareness from Partial Observations
* Full-time Monocular Road Detection Using Zero-distribution Prior of Angle of Polarization
* Fully Convolutional Networks for Continuous Sign Language Recognition
* Fully Embedding Fast Convolutional Networks on Pixel Processor Arrays
* Fully Trainable and Interpretable Non-local Sparse Models for Image Restoration
* Funnel Activation for Visual Recognition
* G-LBM: Generative Low-dimensional Background Model Estimation from Video Sequences
* Gabor Layers Enhance Network Robustness
* Gait Lateral Network: Learning Discriminative and Compact Representations for Gait Recognition
* Gait Recognition from a Single Image Using a Phase-aware Gait Cycle Reconstruction Network
* GAN Slimming: All-in-one GAN Compression by a Unified Optimization Framework
* GAN-based Garment Generation Using Sewing Pattern Images
* Ganhopper: Multi-hop GAN for Unsupervised Image-to-image Translation
* Ganwriting: Content-conditioned Generation of Styled Handwritten Word Images
* GATCluster: Self-supervised Guassian-attention Network for Image Clustering
* GDUMB: A Simple Approach that Questions Our Progress in Continual Learning
* Gelato: Generative Latent Textured Objects
* GEN-Lanenet: A Generalized and Scalable Approach for 3d Lane Detection
* General 3d Room Layout from a Single View by Render-and-compare
* Generalization of Otsu's Method and Minimum Error Thresholding, A
* Generalizing Person Re-identification by Camera-aware Invariance Learning and Cross-Domain Mixup
* Generate to Adapt: Resolution Adaption Network for Surveillance Face Recognition
* Generating Handwriting via Decoupled Style Descriptors
* Generating Videos of Zero-shot Compositions of Actions and Objects
* Generative Low-Bitwidth Data Free Quantization
* Generative Sparse Detection Networks for 3d Single-shot Object Detection
* Generative View-Correlation Adaptation for Semi-Supervised Multi-View Learning
* Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS, A
* Generic Visualization Approach for Convolutional Neural Networks, A
* Geograph: Graph-based Multi-view Object Detection with Geometric Cues End-to-end
* Geolayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes
* Geometric Correspondence Fields: Learned Differentiable Rendering for 3d Pose Refinement in the Wild
* Geometric Estimation via Robust Subspace Recovery
* Geometry Constrained Weakly Supervised Object Localization
* GiNet: Graph Interaction Network for Scene Parsing
* GIQA: Generated Image Quality Assessment
* Global and Local Enhancement Networks for Paired and Unpaired Image Enhancement
* Global Distance-distributions Separation for Unsupervised Person Re-identification
* Global-and-local Relative Position Embedding for Unsupervised Video Summarization
* Globally Optimal and Efficient Vanishing Point Estimation in Atlanta World
* Globally-optimal Event Camera Motion Estimation
* Gmnet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild
* Grab: A Dataset of Whole-body Human Grasping of Objects
* Gradient Centralization: A New Optimization Technique for Deep Neural Networks
* Gradient-Induced Co-Saliency Detection
* Graph Convolutional Networks for Learning with Few Clean and Many Noisy Labels
* Graph Edit Distance Reward: Learning to Edit Scene Graph
* Graph Wasserstein Correlation Analysis for Movie Retrieval
* Graph-based Social Relation Reasoning
* Graph-pcnn: Two Stage Human Pose Estimation with Graph Pose Refinement
* Grnet: Gridding Residual Network for Dense Point Cloud Completion
* Gross: Group-size Series Decomposition for Grouped Architecture Search
* Grounded Situation Recognition
* Group Activity Prediction with Sequential Relational Anticipation Model
* Group Loss for Deep Metric Learning, The
* GSIR: Generalizable 3d Shape Interpretation and Reconstruction
* Gsnet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision
* Guessing State Tracking for Visual Dialogue
* Guidance and Evaluation: Semantic-aware Image Inpainting for Mixed Scenes
* Guided Collaborative Training for Pixel-Wise Semi-Supervised Learning
* Guided Deep Decoder: Unsupervised Image Pair Fusion
* Guided Saliency Feature Learning for Person Re-identification in Crowded Scenes
* Guided Semantic Flow
* Guiding Monocular Depth Estimation Using Depth-attention Volume
* H3dnet: 3d Object Detection Using Hybrid Geometric Primitives
* Hallucinating Visual Instances in Total Absentia
* Halo: Hardware-aware Learning to Optimize
* Hamiltonian Dynamics for Real-world Shape Interpolation
* Hand-transformer: Non-autoregressive Structured Modeling for 3d Hand Pose Estimation
* Handcrafted Outlier Detection Revisited
* Hard Negative Examples are Hard, but Useful
* Hard-Net: Hardness-aware Discrimination Network for 3d Early Activity Prediction
* Hardgan: A Haze-aware Representation Distillation Gan for Single Image Dehazing
* Hdnet: Human Depth Estimation for Multi-person Camera-space Localization
* Hessian Penalty: A Weak Prior for Unsupervised Disentanglement, The
* HGNet: Hybrid Generative Network for Zero-shot Domain Adaptation
* Hidden Footprints: Learning Contextual Walkability from 3d Human Trails
* Hierarchical Context Embedding for Region-based Object Detection
* Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection
* Hierarchical Face Aging Through Disentangled Latent Characteristics
* Hierarchical Kinematic Human Mesh Recovery
* Hierarchical Style-based Networks for Motion Synthesis
* Hierarchical Visual-textual Graph for Temporal Activity Localization via Language
* High Resolution Zero-shot Domain Adaptation of Synthetically Rendered Face Images
* High-fidelity Synthesis with Disentangled Representation
* High-quality Single-model Deep Video Compression with Frame-Conv3D and Multi-frame Differential Modulation
* High-resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling
* Highly Efficient Salient Object Detection with 100k Parameters
* History Repeats Itself: Human Motion Prediction via Motion Attention
* Hmor: Hierarchical Multi-person Ordinal Relations for Monocular Multi-person 3d Pose Estimation
* HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs
* Houghnet: Integrating Near and Long-range Evidence for Bottom-up Object Detection
* House-gan: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation
* How Can I See My Future? FvTraj: Using First-person View for Pedestrian Trajectory Prediction
* How Does Lipschitz Regularization Influence GAN Training?
* Html: A Parametric Hand Texture Model for 3d Hand Reconstruction and Personalization
* Human Body Model Fitting by Learned Gradient Descent
* Human Correspondence Consensus for 3d Object Semantic Understanding
* Human Interaction Learning on 3d Skeleton Point Clouds for Video Violence Recognition
* Hybrid Models for Open Set Recognition
* I2l-meshnet: Image-to-lixel Prediction Network for Accurate 3d Human Pose and Mesh Estimation from a Single RGB Image
* iCaps: An Interpretable Classifier via Disentangled Capsule Networks
* Identity-Aware Multi-Sentence Video Description
* Identity-guided Human Semantic Parsing for Person Re-identification
* Image Classification in the Dark Using Quanta Image Sensors
* Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices, An
* Image Stitching and Rectification for Hand-held Cameras
* Image-Based Table Recognition: Data, Model, and Evaluation
* Image-to-voxel Model Translation for 3d Scene Reconstruction and Segmentation
* Imaging Behind Occluders Using Two-bounce Light
* Imbalanced Continual Learning with Partitioning Reservoir Sampling
* Impact of Base Dataset Design on Few-shot Image Classification
* Implicit Latent Variable Model for Scene-consistent Motion Forecasting
* Improved Adversarial Training via Learned Optimizer
* Improving 3D Object Detection Through Progressive Population Based Augmentation
* Improving Adversarial Robustness by Enforcing Local and Global Compactness
* Improving Deep Video Compression by Resolution-adaptive Flow Coding
* Improving Face Recognition by Clustering Unlabeled Faces in the Wild
* Improving Face Recognition from Hard Samples via Distribution Distillation Loss
* Improving Knowledge Distillation via Category Structure
* Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets
* Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems
* Improving Object Detection with Selective Self-supervised Self-training
* Improving One-Stage Visual Grounding by Recursive Sub-query Construction
* Improving Optical Flow on a Pyramid Level
* Improving Query Efficiency of Black-box Adversarial Attack
* Improving Semantic Segmentation via Decoupled Body and Edge Supervision
* Improving the Transferability of Adversarial Examples with Resized-diverse-inputs, Diversity-ensemble and Region Fitting
* Improving Vision-and-language Navigation with Image-text Pairs from the Web
* In-Domain GAN Inversion for Real Image Editing
* In-home Daily-life Captioning Using Radio Signals
* Inclusive GAN: Improving Data and Minority Coverage in Generative Models
* Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation
* Increasing the Robustness of Semantic Segmentation Models with Painting-by-numbers
* Incremental Few-shot Meta-learning via Indirect Discriminant Alignment
* Indirect Local Attacks for Context-aware Semantic Segmentation Networks
* Inducing Optimal Attribute Representations for Conditional GANs
* Inequality-constrained and Robust 3d Face Model Fitting
* Inertial Safety from Structured Light
* Inference Algorithm for Multi-label MRF-MAP Problems with Clique Size 100, An
* Inference Graphs for CNN Interpretation
* Info3D: Representation Learning on 3D Objects Using Mutual Information Maximization and Contrastive Learning
* Infofocus: 3d Object Detection for Autonomous Driving with Dynamic Information Modeling
* Informative Sample Mining Network for Multi-domain Image-to-image Translation
* Infrastructure-based Multi-camera Calibration Using Radial Projections
* Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-linear Activations
* Instance Adaptive Self-training for Unsupervised Domain Adaptation
* Instance-aware Embedding for Point Cloud Instance Segmentation
* Inter-image Communication for Weakly Supervised Localization
* Interactive Annotation of 3d Object Geometry Using 2d Scribbles
* Interactive Multi-dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration
* Interactive Video Object Segmentation Using Global and Local Transfer Modules
* Interhand2.6m: A Dataset and Baseline for 3d Interacting Hand Pose Estimation from a Single RGB Image
* Interpretable and Generalizable Person Re-identification with Query-adaptive Convolution and Temporal Lifting
* Interpretable Foreground Object Search as Knowledge Distillation
* Interpretable Neural Network Decoupling
* Interpretable Visual Reasoning via Probabilistic Formulation Under Natural Supervision
* Intra-class Feature Variation Distillation for Semantic Segmentation
* Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation
* Invertible Image Rescaling
* Invertible Neural BRDF for Object Inverse Rendering
* Invertible Zero-Shot Recognition Flows
* Is Sharing of Egocentric Video Giving Away Your Biometric Signature?
* It Is Not the Journey But the Destination: Endpoint Conditioned Trajectory Prediction
* Iterative Distance-aware Similarity Matrix Convolution with Mutual-supervised Point Elimination for Efficient Point Cloud Registration
* Iterative Feature Transformation for Fast and Versatile Universal Style Transfer
* JGR-P2O: Joint Graph Reasoning Based Pixel-to-offset Prediction Network for 3d Hand Pose Estimation from a Single Depth Image
* JNR: Joint-based Neural Rig Representation for Compact 3d Face Modeling
* Joint 3d Layout and Depth Prediction from a Single Indoor Panorama Image
* Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer
* Joint Disentangling and Adaptation for Cross-domain Person Re-identification
* Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos
* Joint Optimization for Multi-person Shape Models from Markerless 3d-scans
* Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-identification
* Jointly De-biasing Face Recognition and Demographic Attribute Estimation
* Jointly Learning Visual Motion and Confidence from Local Patches in Event Cameras
* Journey Towards Tiny Perceptual Super-Resolution
* JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds
* JSSR: A Joint Synthesis, Segmentation, and Registration System for 3D Multi-modal Image Alignment of Large-scale Pathological CT Scans
* Jstasr: Joint Size and Transparency-aware Snow Removal Algorithm Based on Modified Partial Convolution and Veiling Effect Removal
* Kernelized Memory Network for Video Object Segmentation
* Key Frame Proposal Network for Efficient Pose Estimation in Videos
* Kinematic 3d Object Detection in Monocular Video
* Kinship Identification Through Joint Learning Using Kinship Verification Ensembles
* Know Your Surroundings: Exploiting Scene Information for Object Tracking
* Knowledge Distillation Meets Self-Supervision
* Knowledge Transfer via Dense Cross-layer Mutual-distillation
* Knowledge-based Video Question Answering with Unsupervised Scene Descriptions
* Label Propagation with Augmented Anchors: A Simple Semi-supervised Learning Baseline for Unsupervised Domain Adaptation
* Label-driven Reconstruction for Domain Adaptation in Semantic Segmentation
* Label-efficient Learning on Point Clouds Using Approximate Convex Decompositions
* Label-similarity Curriculum Learning
* LabelEnc: A New Intermediate Supervision Method for Object Detection
* Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3d Reconstruction with Symmetry
* Landscapear: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors
* Large Batch Optimization for Object Detection: Training Coco in 12 minutes
* Large Scale Holistic Video Understanding
* Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks, A
* Large-scale Few-shot Learning via Multi-modal Knowledge Discovery
* Large-scale Pretraining for Visual Dialog: A Simple State-of-the-art Baseline
* Latent Embedding Feedback and Discriminative Features for Zero-shot Classification
* Latent Topic-aware Multi-label Classification
* Latticenet: Towards Lightweight Image Super-resolution with Lattice Block
* Layer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs
* Layered Neighborhood Expansion for Incremental Multiple Graph Matching
* Laying the Foundations of Deep Long-term Crowd Flow Prediction
* Learn Distributed GAN with Temporary Discriminators
* Learn to Propagate Reliably on Noisy Affinity Graphs
* Learn to Recover Visible Color for Video Surveillance in a Day
* Learnable Cost Volume Using the Cayley Representation
* Learning 3d Part Assembly from a Single Image
* Learning Actionness via Long-range Temporal Order Verification
* Learning and Aggregating Deep Local Descriptors for Instance-Level Recognition
* Learning and Memorizing Representative Prototypes for 3d Point Cloud Semantic and Instance Segmentation
* Learning Architectures for Binary Networks
* Learning Attentive and Hierarchical Representations for 3D Shape Recognition
* Learning Camera-aware Noise Models
* Learning Canonical Representations for Scene Graph to Image Generation
* Learning Connectivity of Neural Networks from a Topological Perspective
* Learning Data Augmentation Strategies for Object Detection
* Learning Delicate Local Representations for Multi-person Pose Estimation
* Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation
* Learning Disentangled Feature Representation for Hybrid-Distorted Image Restoration
* Learning Disentangled Representations via Mutual Information Estimation
* Learning Disentangled Representations with Latent Variation Predictability
* Learning Enriched Features for Real Image Restoration and Enhancement
* Learning Event-driven Video Deblurring and Interpolation
* Learning Feature Descriptors Using Camera Pose Supervision
* Learning Feature Embeddings for Discriminant Model Based Tracking
* Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision
* Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization
* Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification
* Learning from Scale-invariant Examples for Domain Adaptation in Semantic Segmentation
* Learning Gradient Fields for Shape Generation
* Learning Graph-convolutional Representations for Point Cloud Denoising
* Learning Joint Spatial-temporal Transformations for Video Inpainting
* Learning Joint Visual Semantic Matching Embeddings for Language-guided Retrieval
* Learning Lane Graph Representations for Motion Forecasting
* Learning Latent Representations Across Multiple Data Domains Using Lifelong VaeGAN
* Learning Memory Augmented Cascading Network for Compressed Sensing of Images
* Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos
* Learning Monocular Visual Odometry via Self-supervised Long-term Modeling
* Learning Multi-layer Latent Variable Model via Variational Optimization of Short Run MCMC for Approximate Inference
* Learning Noise-aware Encoder-decoder from Noisy Labels by Alternating Back-propagation for Saliency Detection
* Learning Object Depth from Camera Motion and Video Object Segmentation
* Learning Object Permanence from Video
* Learning Object Placement by Inpainting for Compositional Data Augmentation
* Learning Object Relation Graph and Tentative Policy for Visual Navigation
* Learning Open Set Network with Discriminative Reciprocal Points
* Learning Pairwise Inter-plane Relations for Piecewise Planar Reconstruction
* Learning Permutation Invariant Representations Using Memory Networks
* Learning Predictive Models from Observation and Interaction
* Learning Progressive Joint Propagation for Human Motion Prediction
* Learning Propagation Rules for Attribution Map Generation
* Learning Semantic Neural Tree for Human Parsing
* Learning Stereo from Single Images
* Learning Structural Similarity of User Interface Layouts Using Graph Networks
* Learning Surrogates via Deep Embedding
* Learning to Balance Specificity and Invariance for In and Out of Domain Generalization
* Learning to Cluster Under Domain Shift
* Learning to Combine: Knowledge Aggregation for Multi-source Domain Adaptation
* Learning to Compose Hypercolumns for Visual Correspondence
* Learning to Count in the Crowd from Limited Labeled Data
* Learning to Detect Open Classes for Universal Domain Adaptation
* Learning to Exploit Multiple Vision Modalities by Using Grafted Networks
* Learning to Factorize and Relight a City
* Learning to Generate Customized Dynamic 3d Facial Expressions
* Learning to Generate Grounded Visual Captions Without Localization Supervision
* Learning to Generate Novel Domains for Domain Generalization
* Learning to Learn in a Semi-Supervised Fashion
* Learning to Learn Parameterized Classification Networks for Scalable Input Images
* Learning to Learn with Variational Information Bottleneck for Domain Generalization
* Learning to Learn Words from Visual Scenes
* Learning to Localize Actions from Moments
* Learning to Optimize Domain Specific Normalization for Domain Generalization
* Learning to Plan with Uncertain Topological Maps
* Learning to Predict Context-adaptive Convolution for Semantic Segmentation
* Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model
* Learning to Scale Multilingual Representations for Vision-Language Tasks
* Learning to See in the Dark with Events
* Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes
* Learning to Transfer Learn: Reinforcement Learning-based Selection for Adaptive Transfer Learning
* Learning Trailer Moments in Full-length Movies with Co-contrastive Attention
* Learning Visual Commonsense for Robust Scene Graph Generation
* Learning Visual Context by Comparison
* Learning Visual Representations with Caption Annotations
* Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision
* Learning What to Learn for Video Object Segmentation
* Learning Where to Focus for Efficient Video Object Detection
* Learning with Noisy Class Labels for Instance Segmentation
* Learning with Privileged Information for Efficient Image Super-resolution
* Least Squares Surface Reconstruction on Arbitrary Domains
* LEED: Label-free Expression Editing via Disentanglement
* Lemma: A Multi-view Dataset for Learning Multi-agent Multi-task Activities
* Length-controllable Image Captioning
* Lensless Imaging with Focusing Sparse Ura Masks in Long-wave Infrared and Its Application for Human Detection
* Levelset R-CNN: A Deep Variational Method for Instance Segmentation
* Leveraging Acoustic Images for Effective Self-supervised Audio Representation Learning
* Leveraging Seen and Unseen Semantic Relationships for Generative Zero-shot Learning
* Lifespan Age Transformation Synthesis
* Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
* LIMP: Learning Latent Shape Representations with Metric Preservation Priors
* Linguistic Structure Guided Context Modeling for Referring Image Segmentation
* LIRA: Lifelong Image Restoration from Unknown Blended Distortions
* LiteFlownet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation
* Local Correlation Consistency for Knowledge Distillation
* Localizing the Common Action Among a Few Videos
* Location Sensitive Image Retrieval and Tagging
* Long-term Human Motion Prediction with Scene Context
* Look Here! A Parametric Learning Based Approach to Redirect Visual Attention
* Look Ma, No Landmarks!: Unsupervised, Model-based Dense Face Alignment
* Low Light Video Enhancement Using Synthetic Data Produced with an Intermediate Domain Mapping
* Lst-net: Learning a Convolutional Neural Network with a Learnable Sparse Transform
* LSTM Approach to Temporal 3d Object Detection in Lidar Point Clouds, An
* Mabnet: A Lightweight Stereo Network Based on Multibranch Adjustable Bottleneck Module
* Making Affine Correspondences Work in Camera Geometry Computation
* Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors
* Making Sense of CNNs: Interpreting Deep Representations and Their Invariances with INNs
* Malleable 2.5d Convolution: Learning Receptive Fields Along the Depth-axis for RGB-D Scene Parsing
* Manifold Projection for Adversarial Defense on Face Recognition
* Many-shot from Low-shot: Learning to Annotate Using Mixed Supervision for Object Detection
* Mapillary Planet-Scale Depth Dataset
* Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale, The
* Mapping in a Cycle: Sinkhorn Regularized Unsupervised Learning for Point Cloud Shapes
* Margin-mix: Semi-supervised Learning for Face Expression Recognition
* Mask Textspotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
* Mask2CAD: 3d Shape Prediction by Learning to Segment and Retrieve
* Matching Guided Distillation
* Matryodshka: Real-time 6dof Video View Synthesis Using Multi-sphere Images
* Mead: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation
* Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3d Hand Pose Estimation Under Hand-object Interaction
* Measuring the Importance of Temporal Features in Video Saliency
* Memory Selection Network for Video Propagation
* Memory-augmented Dense Predictive Coding for Video Representation Learning
* Memory-efficient Incremental Learning Through Feature Adaptation
* Meshing Point Clouds with Predicted Intrinsic-extrinsic Ratio Guidance
* MessyTable: Instance Association in Multiple Camera Views
* Meta-learning with Network Pruning
* Meta-RPPG: Remote Heart Rate Estimation Using a Transductive Meta-learner
* Meta-SIM2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
* Metadistiller: Network Self-boosting via Meta-learned Top-down Distillation
* Metric Learning Reality Check, A
* Microscopy Image Restoration with Deep Wiener-Kolmogorov Filters
* MimicDet: Bridging the Gap Between One-stage and Two-stage Object Detection
* Mind the Discriminability: Asymmetric Adversarial Domain Adaptation
* Mini-Net: Multiple Instance Ranking Network for Video Highlight Detection
* Minimal Rolling Shutter Absolute Pose with Unknown Focal Length and Radial Distortion
* Minimum Class Confusion for Versatile Domain Adaptation
* Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation
* Mining Inter-video Proposal Relations for Video Object Detection
* Mining Self-similarity: Label Super-resolution with Epitomic Representations
* Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification
* Model-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot Learning
* Model-based Occlusion Disentanglement for Image-to-Image Translation
* Modeling 3D Shapes by Reinforcement Learning
* Modeling Artistic Workflows for Image Generation and Editing
* Modeling the Effects of Windshield Refraction for Camera Calibration
* Modeling the Space of Point Landmark Constrained Diffeomorphisms
* Momentum Batch Normalization for Deep Learning with Small Batch Size
* Monocular 3d Object Detection via Feature Domain Adaptation
* Monocular Differentiable Rendering for Self-supervised 3D Object Detection
* Monocular Expressive Body Regression Through Body-Driven Attention
* Monocular Real-time Volumetric Performance Capture
* Monotonicity Prior for Cloud Tomography
* More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning
* Motion Capture from Internet Videos
* Motion Guided 3d Pose Estimation from Videos
* Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
* Motionsqueeze: Neural Motion Feature Learning for Video Understanding
* Movienet: A Holistic Dataset for Movie Understanding
* MPCC: Matching Priors and Conditionals for Clustering
* Mti-net: Multi-scale Task Interaction Networks for Multi-task Learning
* MuCAN: Multi-correspondence Aggregation Network for Video Super-resolution
* Multi-agent Embodied Question Answering in Interactive Environments
* Multi-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed Video
* Multi-loss Rebalancing Algorithm for Monocular Depth Estimation
* Multi-modal Transformer for Video Retrieval
* Multi-person 3d Pose Estimation in Crowded Scenes Based on Multi-view Geometry
* Multi-scale Positive Sample Refinement for Few-shot Object Detection
* Multi-source Open-set Deep Adversarial Domain Adaptation
* Multi-task Curriculum Framework for Open-set Semi-supervised Learning
* Multi-temporal Recurrent Neural Networks for Progressive Non-uniform Single Image Deblurring with Incremental Temporal Training
* Multi-view Action Recognition Using Cross-view Video Prediction
* Multi-view Adaptive Graph Convolutions for Graph Classification
* Multi-view Optimization of Local Feature Geometry
* Multimodal Memorability: Modeling Effects of Semantics and Decay on Video Memorability
* Multimodal Shape Completion via Conditional Generative Adversarial Networks
* Multiple Class Novelty Detection Under Data Distribution Shift
* Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
* Multiple Sound Sources Localization from Coarse to Fine
* Multitask Learning Strengthens Adversarial Robustness
* Multiview Detection with Feature Perspective Transformation
* MutualNet: Adaptive Convnet via Mutual Learning from Network Width and Resolution
* n-reference Transfer Learning for Saliency Prediction
* Naive-Student: Leveraging Semi-supervised Learning in Video Sequences for Urban Scene Segmentation
* NAS-Count: Counting-by-density with Neural Architecture Search
* NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
* NASA Neural Articulated Shape Approximation
* Negative Margin Matters: Understanding Margin in Few-Shot Classification
* Negative Pseudo Labeling Using Class Proportion for Semantic Segmentation in Pathology
* NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
* Neural Batch Sampling with Reinforcement Learning for Semi-Supervised Anomaly Detection
* Neural Dense Non-rigid Structure from Motion with Latent Space Constraints
* Neural Design Network: Graphic Layout Generation with Constraints
* Neural Geometric Parser for Single Image Camera Calibration
* Neural Hair Rendering
* Neural Object Learning for 6d Pose Estimation Using a Few Cluttered Images
* Neural Point-based Graphics
* Neural Predictor for Neural Architecture Search
* Neural Re-rendering of Humans from a Single Image
* Neural Voice Puppetry: Audio-driven Facial Reenactment
* Neural Wireframe Renderer: Learning Wireframe to Image Translations
* Neurora: Neural Robust Rotation Averaging
* New Threats Against Object Detector with Non-local Block
* Nighttime Defogging Using High-low Frequency Decomposition and Grayscale-color Networks
* Nodis: Neural Ordinary Differential Scene Understanding
* Noiserank: Unsupervised Label Noise Reduction with Dependence Models
* Non-local Spatial Propagation Network for Depth Completion
* Normalgan: Learning Detailed 3d Human from a Single RGB-D Image
* Not only Look, But Also Listen: Learning Multimodal Violence Detection Under Weak Supervision
* Novel Line Integral Transform for 2d Affine-Invariant Shape Retrieval, A
* Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-encoder
* Nsganetv2: Evolutionary Multi-objective Surrogate-assisted Neural Architecture Search
* Null-sampling for Interpretable and Fair Representations
* Object as Hotspots: An Anchor-free 3d Object Detection Approach via Firing of Hotspots
* Object Detection with a Unified Label Space from Multiple Datasets
* Object Tracking Using Spatio-temporal Networks for Future Prediction Location
* Object-and-action Aware Model for Visual Language Navigation
* Object-based Illumination Estimation with Rendering-aware Neural Networks
* Object-contextual Representations for Semantic Segmentation
* Occlusion-aware Depth Estimation with Adaptive Normal Constraints
* Occlusion-aware Siamese Network for Human Pose Estimation
* Occupancy Anticipation for Efficient Exploration and Navigation
* Ocean: Object-aware Anchor-free Tracking
* Off-policy Reinforcement Learning for Efficient and Effective GAN Architecture Search
* Oid: Outlier Identifying and Discarding in Blind Image Deblurring
* Omni-sourced Webly-supervised Learning for Video Recognition
* On Disentangling Spoof Trace for Generic Face Anti-spoofing
* On Diverse Asynchronous Activity Anticipation
* On Dropping Clusters to Regularize Graph Convolutional Neural Networks
* On Modulating the Gradient for Meta-learning
* On the Effectiveness of Image Rotation for Open Set Domain Adaptation
* On the Usage of the Trifocal Tensor in Motion Segmentation
* On Transferability of Histological Tissue Labels in Computational Pathology
* One-pixel Signature: Characterizing CNN Models for Backdoor Detection
* One-shot Unsupervised Cross-Domain Detection
* OneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-grained Clustering
* Online Continual Learning Under Extreme Memory Constraints
* Online Ensemble Model Compression Using Knowledge Distillation
* Online Invariance Selection for Local Feature Descriptors
* Online Meta-learning for Multi-source and Semi-supervised Domain Adaptation
* Online Multi-modal Person Search in Videos
* Onlineaugment: Online Data Augmentation with Less Domain Knowledge
* Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions
* Open-set Adversarial Defense
* Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer
* Orderly Disorder in Point Cloud Domain
* Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network
* Os2d: One-stage One-shot Object Detection by Matching Anchor Features
* OSCAR: Object-Semantics Aligned Pre-Training for Vision-Language Tasks
* P2 Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation
* Packdet: Packed Long-Head Object Detector
* Pairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization
* PAMS: Quantized Super-resolution via Parameterized Max Scale
* Parsenet: A Parametric Surface Fitting Network for 3d Point Clouds
* Part-aware Prototype Network for Few-Shot Semantic Segmentation
* Partially-shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift
* Particularity Beyond Commonality: Unpaired Identity Transfer with Multiple References
* Password-conditioned Anonymization and Deanonymization with Face Identity Transformers
* Patch-wise Attack for Fooling Deep Neural Network
* Patchattack: A Black-box Texture-based Attack with Reinforcement Learning
* Patchnets: Patch-based Generalizable Deep Implicit 3d Shape Representations
* PatchPerPix for Instance Segmentation
* Peeking into Occluded Joints: A Novel Framework for Crowd Pose Estimation
* People as Scene Probes
* Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations
* Perceiving 3d Human-object Spatial Arrangements from a Single Image in the Wild
* Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting
* PG-Net: Pixel to Global Matching Network for Visual Tracking
* Phong Surface: Efficient 3d Model Fitting Using Lifted Optimization, The
* Photon-efficient 3d Imaging with A Non-local Neural Network
* Phraseclick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click
* Physics-based Feature Dehazing Networks
* Pienet: Personalized Image Enhancement Network
* Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation
* Pillar-based Object Detection for Autonomous Driving
* Piou Loss: Towards Accurate Oriented Object Detection in Complex Environments
* PIP: Planning-informed Trajectory Prediction for Autonomous Driving
* Pipal: A Large-scale Image Quality Assessment Dataset for Perceptual Image Restoration
* Pix2Surf: Learning Parametric 3d Surface Models of Objects from Images
* Pixel-Pair Occlusion Relationship Map (P2ORM): Formulation, Inference and Application
* Pl1P: Point-line Minimal Problems Under Partial Visibility in Three Views
* Placepedia: Comprehensive Place Understanding with Multi-faceted Annotations
* Plugnet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-resolution Unit
* Podnet: Pooled Outputs Distillation for Small-tasks Incremental Learning
* Point-set Anchors for Object Detection, Instance Segmentation and Pose Estimation
* Pointar: Efficient Lighting Estimation for Mobile Augmented Reality
* Pointcontrast: Unsupervised Pre-training for 3d Point Cloud Understanding
* PointMixup: Augmentation for Point Clouds
* Pointpwc-net: Cost Volume on Point Clouds for (self-)supervised Scene Flow Estimation
* Points2surf Learning Implicit Surfaces from Point Clouds
* Pointtrinet: Learned Triangulation of 3d Point Sets
* Polarimetric Multi-View Inverse Rendering
* Polarized Optical-flow Gyroscope
* Polynomial Regression Network for Variable-number Lane Detection
* Polysemy Deciphering Network for Human-object Interaction Detection
* Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition
* Pose2mesh: Graph Convolutional Network for 3d Human Pose and Mesh Recovery from a 2d Human Pose
* Post-training Piecewise Linear Quantization for Deep Neural Networks
* Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
* Practical Deep Raw Image Denoising on Mobile Devices
* Practical Detection of Trojan Neural Networks: Data-limited and Data-free Cases
* Practical Poisoning Attacks on Neural Networks
* Predicting Visual Overlap of Images Through Interpretable Non-metric Box Embeddings
* Prediction and Recovery for Adaptive Low-resolution Person Re-identification
* Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval
* Prime-aware Adaptive Distillation
* Principal Feature Visualisation in Convolutional Neural Networks
* Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions
* Privacy Preserving Structure-from-motion
* Privacy Preserving Visual SLAM
* Probabilistic Anchor Assignment with IoU Prediction for Object Detection
* Probabilistic Future Prediction for Video Scene Understanding
* Procedure Planning in Instructional Videos
* Procrustean Regression Networks: Learning 3d Structure of Non-rigid Objects from 2d Annotations
* Profit: A Novel Training Method for sub-4-bit Mobilenet Models
* Progressface: Scale-aware Progressive Learning for Face Detection
* Progressive Point Cloud Deconvolution Generation Network
* Progressive Refinement Network for Occluded Pedestrian Detection
* Progressive Transformers for End-to-end Sign Language Production
* Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection
* Propagating Over Phrase Relations for One-stage Visual Grounding
* Proposal-based Video Completion
* Prototype Mixture Models for Few-shot Semantic Segmentation
* Prototype Rectification for Few-shot Learning
* Proxybnn: Learning Binarized Neural Networks via Proxy Matrices
* ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis
* PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer
* Pseudo RGB-D for Self-improving Monocular SLAM and Depth Prediction
* Pt2pc: Learning to Generate 3d Point Cloud Shapes from Part Tree Conditions
* Pugeo-net: A Geometry-centric Network for 3d Point Cloud Upsampling
* Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation
* Quantization Guided JPEG Artifact Correction
* Quantum-soft Qubo Suppression for Accurate Object Detection
* Quaternion Equivariant Capsule Networks for 3d Point Clouds
* Quest: Quantized Embedding Space for Transferring Knowledge
* Radarnet: Exploiting Radar for Robust Perception of Dynamic Objects
* Raft: Recurrent All-pairs Field Transforms for Optical Flow
* RANSAC-flow: Generic Two-stage Image Alignment
* RBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax
* RD-GAN: Few/zero-shot Chinese Character Style Transfer via Radical Decomposition and Rendering
* Reactnet: Towards Precise Binary Neural Network with Generalized Activation Functions
* READ: Reciprocal Attention Discriminator for Image-to-Video Re-identification
* Real-world Blur Dataset for Learning and Benchmarking Deblurring Algorithms
* Reconstructing NBA Players
* Reconstructing the Noise Variance Manifold for Image Denoising
* Recurrent Image Annotation with Explicit Inter-Label Dependencies
* Recurrent Transformer Network for Novel View Action Synthesis, A
* Redro: Efficiently Learning Large-sized SPD Visual Representation
* Reducing Distributional Uncertainty by Mutual Information Maximisation and Transferable Feature Learning
* Reducing Language Biases in Visual Question Answering with Visually-grounded Question Encoder
* Reducing the Sim-to-real Gap for Event Cameras
* Referit3d: Neural Listeners for Fine-grained 3d Object Identification in Real-world Scenes
* Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
* Reflection Separation via Multi-bounce Polarization State Tracing
* Region Graph Embedding Network for Zero-shot Learning
* Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
* Regression of Instance Boundary by Aggregated CNN and GCN
* Regularization with Latent Space Virtual Adversarial Training
* Regularized Loss for Weakly Supervised Single Class Semantic Segmentation
* Reinforced Axial Refinement Network for Monocular 3d Object Detection
* Relative Pose Estimation of Calibrated Cameras with Known Se(3) Invariants
* Relative Pose from Deep Learned Depth and a Single Affine Correspondence
* Remind Your Neural Network to Prevent Catastrophic Forgetting
* Renovating Parsing R-CNN for Accurate Multiple Human Parsing
* Reparameterizing Convolutions for Incremental Multi-Task Learning Without Task Interference
* Representation Learning on Visual-Symbolic Graphs for Video Understanding
* Representation Sharing for Fast Object Detector Search and Beyond
* Representative Graph Neural Network
* Representative-Discriminative Learning for Open-Set Land Cover Classification of Satellite Imagery
* Resolution Switchable Networks for Runtime Efficient Image Recognition
* Rethinking Bottleneck Structure for Efficient Mobile Network Design
* Rethinking Class Activation Mapping for Weakly Supervised Object Localization
* Rethinking Few-shot Image Classification: A Good Embedding is All You Need?
* Rethinking Image Deraining via Rain Streaks and Vapors
* Rethinking Image Inpainting via a Mutual Encoder-decoder with Feature Equalizations
* Rethinking Pseudo-Lidar Representation
* Rethinking the Defocus Blur Detection Problem and a Real-time Deep Dbd Model
* Rethinking the Distribution Gap of Person Re-identification with Camera-Based Batch Normalization
* RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval
* Reversing the Cycle: Self-supervised Deep Stereo Through Enhanced Monocular Distillation
* REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets
* Rewriting a Deep Generative Model
* RGB-D Salient Object Detection with Cross-modality Modulation and Selection
* Rhyrnn: Rhythmic RNN for Recognizing Events in Long and Complex Videos
* Robust and On-the-Fly Dataset Denoising for Image Classification
* Robust Neural Networks Inspired by Strong Stability Preserving Runge-Kutta Methods
* Robust Re-identification by Multiple Views Knowledge Distillation
* Robust Tracking Against Adversarial Attacks
* Robustfusion: Human Volumetric Capture with Data-driven Visual Cues Using a RGBD Camera
* Robustscanner: Dynamically Enhancing Positional Clues for Robust Text Recognition
* Rotation-Robust Intersection over Union for 3d Object Detection
* Rotational Outlier Identification in Pose Graphs using Dual Decomposition
* Rotationally-temporally Consistent Novel View Synthesis of Human Performance Video
* RTM3D: Real-time Monocular 3d Detection from Object Keypoints for Autonomous Driving
* RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition
* S2dnas: Transforming Static Cnn Model for Dynamic Inference via Neural Architecture Search
* S2DNet: Learning Image Features for Accurate Sparse-to-Dense Matching
* S3 Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data
* Saca Net: Cybersickness Assessment of Individual Viewers for VR Content via Graph-Based Symptom Relation Embedding
* Sat2graph: Road Graph Extraction Through Graph-tensor Encoding
* Scan: Learning to Classify Images Without Labels
* Scanrefer: 3d Object Localization in RGB-D Scans Using Natural Language
* Scene Text Image Super-Resolution in the Wild
* SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans
* Scenesketcher: Fine-grained Image Retrieval with Scene Sketches
* Scribblebox: Interactive Annotation Framework for Video Object Segmentation
* Search What You Want: Barrier Penalty NAS for Mixed Precision Quantization
* Searching Efficient 3d Architectures with Sparse Point-voxel Convolution
* Seeing the Un-scene: Learning Amodal Semantic Maps for Room Navigation
* Segfix: Model-agnostic Boundary Refinement for Segmentation
* Segment as Points for Efficient Online Multi-object Tracking and Segmentation
* Segmentations-leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation
* Segmenting Transparent Objects in the Wild
* Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
* Self-adapting Confidence Estimation for Stereo
* Self-challenging Improves Cross-domain Generalization
* Self-paced Deep Regression Forests with Consideration on Underrepresented Examples
* Self-prediction for Joint Instance and Semantic Segmentation of Point Clouds
* Self-similarity Student for Partial Label Histopathology Image Segmentation
* Self-supervised Bayesian Deep Learning for Image Recovery with Applications to Compressive Sensing
* Self-Supervised CycleGAN for Object-preserving Image-to-Image Domain Adaptation
* Self-supervised Keypoint Correspondences for Multi-person Pose Estimation and Tracking in Videos
* Self-supervised Learning of Audio-visual Objects from Video
* Self-supervised Monocular 3D Face Reconstruction by Occlusion-aware Multi-view Geometry Consistency
* Self-supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
* Self-supervised Motion Representation via Scattering Local Motion Cues
* Self-supervised Multi-task Procedure Learning from Instructional Videos
* Self-supervised Outdoor Scene Relighting
* Self-supervised Single-view 3d Reconstruction via Semantic Consistency
* Self-supervised Video Representation Learning by Pace Prediction
* Self-supervising Fine-grained Region Similarities for Large-scale Image Localization
* Self-supervision with Superpixels: Training Few-shot Medical Image Segmentation Without Annotation
* Self6d: Self-supervised Monocular 6d Object Pose Estimation
* Semantic Curiosity for Active Visual Learning
* Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering
* Semantic Flow for Fast and Accurate Scene Parsing
* Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching
* Semantic Mutex Watershed for Efficient Bottom-up Semantic Instance Segmentation, The
* Semantic Object Prediction and Spatial Sound Super-resolution with Binaural Sounds
* Semantic Relation Preserving Knowledge Distillation for Image-to-image Translation
* Semantic View Synthesis
* SemantiCADV: Generating Adversarial Examples via Attribute-conditioned Image Editing
* Semi-Siamese Training for Shallow Face Learning
* Semi-Supervised Crowd Counting via Self-training on Surrogate Tasks
* Semi-supervised Learning with a Teacher-student Network for Generalized Attribute Prediction
* Semi-supervised Segmentation Based on Error-correcting Supervision
* Semi-supervised Semantic Segmentation via Strong-weak Dual-branch Network
* SemifreddoNets: Partially Frozen Neural Networks for Efficient Computer Vision Systems
* Sen: A Novel Feature Normalization Dissimilarity Measure for Prototypical Few-shot Learning Networks
* Sep-stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation
* Seqhand: RGB-sequence-based 3d Hand Pose and Shape Estimation
* Sequential Convolution and Runge-Kutta Residual Architecture for Image Compressed Sensing
* Sequential Deformation for Accurate Scene Text Detection
* SeqXY2SeqZ: Structure Learning for 3d Shapes by Sequentially Predicting 1D Occupancy Segments from 2d Coordinates
* Sesame: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects
* SF-net: Single-frame Supervision for Temporal Action Localization
* SG-VAE: Scene Grammar Variational Autoencoder to Generate New Indoor Scenes
* Shape Adaptor: A Learnable Resizing Module
* Shape and Viewpoint Without Keypoints
* Shape Prior Deformation for Categorical 6d Object Pose and Size Estimation
* Shonan Rotation Averaging: Global Optimality by Surfing So(p)n
* Short-term and Long-term Context Aggregation Network for Video Inpainting
* Shuffle and Attend: Video Domain Adaptation
* Side-aware Boundary Localization for More Precise Object Detection
* Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks
* Sideinfnet: A Deep Neural Network for Semi-automatic Semantic Segmentation with Side Information
* SimAug: Learning Robust Representations from Simulation for Trajectory Prediction
* Simple and Effective Framework for Pairwise Deep Metric Learning, A
* Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions, A
* Simplicial Complex Based Point Correspondence Between Images Warped onto Manifolds
* Simpose: Effectively Learning Densepose and Surface Normals of People from Simulated Data
* Simulating Content Consistent Vehicle Datasets with Attribute Descent
* Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking
* Single Image Super-Resolution via a Holistic Attention Network
* Single Path One-shot Neural Architecture Search with Uniform Sampling
* Single Stream Network for Robust and Real-time RGB-D Salient Object Detection, A
* Single View Metrology in the Wild
* Single-image Depth Prediction Makes Feature Matching Easier
* Single-shot Neural Relighting and SVBRDF Estimation
* Sipmask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
* Sizer: A Dataset and Model for Parsing 3d Clothing and Learning Size Sensitive 3d Clothing
* Sketch-guided Object Localization in Natural Images
* Sketching Image Gist: Human-Mimetic Hierarchical Scene Graph Generation
* Smap: Single-shot Multi-person Absolute 3d Pose Estimation
* SMART: Simultaneous Multi-agent Recurrent Trajectory Prediction
* Smooth-AP: Smoothing the Path Towards Large-scale Image Retrieval
* Sne-roadseg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection
* Social Adaptive Module for Weakly-supervised Group Activity Recognition
* Soda: Story Oriented Dense Video Captioning Evaluation Framework
* Soft Anchor-point Object Detection
* Soft Expert Reward Learning for Vision-and-Language Navigation
* Softpoolnet: Shape Descriptor for Point Cloud Completion and Classification
* Solar: Second-order Loss and Attention for Image Retrieval
* SOLO: Segmenting Objects by Locations
* Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier
* Solving Phase Retrieval with a Learned Reference
* Solving the Blind Perspective-n-point Problem End-to-end with Robust Differentiable Geometric Optimization
* Sound2sight: Generating Visual Dynamics from Sound and Context
* Soundspaces: Audio-visual Navigation in 3d Environments
* SPAN: Spatial Pyramid Attention Network for Image Manipulation Localization
* Spark: Spatial-aware Online Incremental Attack Against Visual Tracking
* Sparse Adversarial Attack via Perturbation Factorization
* Sparse-to-dense Depth Completion Revisited: Sampling Strategy and Graph Construction
* Spatial Attention Pyramid Network for Unsupervised Domain Adaptation
* Spatial Geometric Reasoning for Room Layout Estimation via Deep Reinforcement Learning
* Spatial Hierarchy Aware Residual Pyramid Network for Time-of-flight Depth Denoising
* Spatial-adaptive Network for Single Image Denoising
* Spatial-angular Interaction for Light Field Image Super-resolution
* Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation
* Spatially Aware Multimodal Transformers for TextVQA
* Spatio-temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
* Spatiotemporal Attacks for Embodied Agents
* Speech-driven Facial Animation Using Cascaded Gans for Learning of Motion and Texture
* Spherical Feature Transform for Deep Metric Learning
* Spike-flownet: Event-based Optical Flow Estimation with Energy-efficient Hybrid Neural Networks
* Spiral Generative Network for Image Extrapolation
* SPL-MLL: Selecting Predictable Landmarks for Multi-label Learning
* Splitting Vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation
* Spot: Selective Point Cloud Voting for Better Proposal in Point Cloud Object Detection
* Square Attack: A Query-efficient Black-box Adversarial Attack via Random Search
* Squeezesegv3: Spatially-adaptive Convolution for Efficient Point-cloud Segmentation
* Srflow: Learning the Super-resolution Space with Normalizing Flow
* Srnet: Improving Generalization in 3d Human Pose Estimation with a Split-and-recombine Approach
* Sscgan: Facial Attribute Editing via Style Skip Connections
* SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
* Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network
* Stacking Networks Dynamically for Image Restoration Based on the Plug-and-play Framework
* STAR: Sparse Trained Articulated Human Body Regressor
* STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
* Stereo Event-based Particle Tracking Velocimetry for 3d Fluid Flow Reconstruction
* Stochastic Bundle Adjustment for Efficient and Scalable 3d Reconstruction
* Stochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition
* Stochastic Frequency Masking to Improve Super-resolution and Denoising Networks
* Streaming Object Detection for 3-d Point Clouds
* Structural Deep Metric Learning for Room Layout Estimation
* Structure-aware Generation Network for Recipe Generation from Images
* Structure-Aware Human-Action Generation
* Structured Landmark Detection via Topology-adapting Deep Graph Learning
* Structured3D: A Large Photo-realistic Dataset for Structured 3d Modeling
* Style Transfer for Co-speech Gesture Animation: A Multi-speaker Conditional-mixture Approach
* StyleGAN2 Distillation for Feed-forward Image Manipulation
* Sub-center Arcface: Boosting Face Recognition by Large-scale Noisy Web Faces
* Sumgraph: Video Summarization via Recursive Graph Modeling
* Supervised Edge Attention Network for Accurate Image Instance Segmentation
* Suppress and Balance: A Simple Gated Network for Salient Object Detection
* Suppressing Mislabeled Data via Grouping and Self-attention
* Surface Normal Estimation of Tilted Images via Spatial Rectifier
* Symbiotic Adversarial Learning for Attribute-based Person Search
* Synthesis and Completion of Facades from Satellite Imagery
* Synthesize Then Compare: Detecting Failures and Anomalies for Semantic Segmentation
* Synthesizing Coupled 3d Face Modalities by Trunk-branch Generative Adversarial Networks
* Table Structure Recognition Using Top-down and Bottom-up Cues
* Tafssl: Task-adaptive Feature Sub-space Learning for Few-shot Classification
* Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping
* Talking-head Generation with Rhythmic Head Motion
* TANet: Towards Fully Automatic Tooth Arrangement
* TAO: A Large-scale Benchmark for Tracking Any Object
* Targeted Attack for Deep Hashing Based Retrieval
* Task-aware Quantization Network for JPEG Image Compression
* Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery
* TCGM: An Information-theoretic Framework for Semi-supervised Multi-modality Learning
* Teaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces from Images
* Temporal Aggregate Representations for Long-range Video Understanding
* Temporal Coherence or Temporal Motion: Which Is More Critical for Video-based Person Re-identification?
* Temporal Complementary Learning for Video Person Re-identification
* Temporal Distinct Representation Learning for Action Recognition
* Temporal Keypoint Matching and Refinement Network for Pose Estimation and Tracking
* Tenet: Triple Excitation Network for Video Salient Object Detection
* Tensor Low-rank Reconstruction for Semantic Segmentation
* Testing the Safety of Self-driving Vehicles by Simulating Perception and Prediction
* Texmesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video
* Textcaps: A Dataset for Image Captioning with Reading Comprehension
* Texture Hallucination for Large-factor Painting Super-resolution
* TF-NAS: Rethinking Three Search Freedoms of Latency-constrained Differentiable Neural Architecture Search
* Thanks for Nothing: Predicting Zero-valued Activations with Lightweight Convolutional Neural Networks
* Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues
* TIDE: A General Toolbox for Identifying Object Detection Errors
* TopoAL: An Adversarial Learning Approach for Topology-aware Road Segmentation
* Topogan: A Topology-aware Generative Adversarial Network
* Topology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction
* Topology-preserving Class-incremental Learning
* Toward Faster and Simpler Matrix Normalization via Rank-1 Update
* Toward Fine-grained Facial Expression Manipulation
* Toward Unsupervised, Multi-object Discovery in Large-scale Image Collections
* Towards Automated Testing and Robustification by Semantic Adversarial Data Generation
* Towards Causal Benchmarking of Bias in Face Analysis Algorithms
* Towards Content-independent Multi-reference Super-resolution: Adaptive Pattern Matching and Feature Aggregation
* Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition
* Towards End-to-end Video-based Eye-tracking
* Towards Fast, Accurate and Stable 3d Dense Face Alignment
* Towards Generalization Across Depth for Monocular 3d Object Detection
* Towards Part-aware Monocular 3d Human Pose Estimation: An Architecture Search Approach
* Towards Practical and Efficient High-resolution HDR Deghosting with CNN
* Towards Precise Completion of Deformable Shapes
* Towards Real-time Multi-object Tracking
* Towards Recognizing Unseen Categories in Unseen Domains
* Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial Images
* Towards Streaming Perception
* Towards Unique and Informative Captioning of Images
* TP-LSD: Tri-points Based Line Segment Detector
* TPFN: Applying Outer Product Along Time to Multimodal Sentiment Analysis Fusion on Incomplete Data
* Tracking Emerges by Looking Around Static Scenes, with Neural 3d Mapping
* Tracking Objects as Points
* Tradi: Tracking Deep Neural Network Weight Distributions
* Traffic Accident Benchmark for Causality Recognition
* Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters
* Trajectron++: Dynamically-Feasible Trajectory Forecasting with Heterogeneous Data
* Transformation Consistency Regularization: A Semi-supervised Paradigm for Image-to-image Translation
* Transforming and Projecting Images into Class-conditional Generative Networks
* Transporting Labels via Hierarchical Optimal Transport for Semi-supervised Learning
* TRRNET: Tiered Relation Reasoning for Compositional Visual Question Answering
* Truncated Inference for Latent Variable Optimization Problems: Application to Robust Estimation and Learning
* Tsit: A Simple and Versatile Framework for Image-to-image Translation
* TUIGAN: Learning Versatile Image-to-image Translation with Two Unpaired Images
* TVR: A Large-scale Dataset for Video-subtitle Moment Retrieval
* Two Stream Active Query Suggestion for Active Learning in Connectomics
* Two-branch Recurrent Network for Isolating Deepfakes in Videos
* Two-phase Pseudo Label Densification for Self-training Based Domain Adaptation
* Two-stream Consensus Network for Weakly-supervised Temporal Action Localization
* Ufo2: A Unified Framework Towards Omni-supervised Object Detection
* Ultra Fast Structure-aware Deep Lane Detection
* Uncertainty-aware Weakly Supervised Action Detection from Untrimmed Videos
* Unified Framework for Shot Type Classification Based on Subject Centric Lens, A
* Unified Framework of Surrogate Loss by Refactoring and Interpolation, A
* Unified Image and Video Saliency Modeling
* Unified Multisensory Perception: Weakly-supervised Audio-visual Video Parsing
* Unifying Deep Local and Global Features for Image Search
* Unifying Mutual Information View of Metric Learning: Cross-entropy vs. Pairwise Losses, A
* Uniondet: Union-level Detector Towards Real-time Human-object Interaction Detection
* Uniter: Universal Image-Text Representation Learning
* Unpaired Image-to-image Translation Using Adversarial Consistency Loss
* Unpaired Learning of Deep Image Denoising
* Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild
* Unsupervised 3d Human Pose Representation with Viewpoint and Pose Disentanglement
* Unsupervised Cross-modal Alignment for Multi-person 3d Pose Estimation
* Unsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering Loss
* Unsupervised Domain Adaptation for Semantic Segmentation of NIR Images Through Generative Latent Search
* Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification
* Unsupervised Domain Adaptation with Noise Resistible Mutual-training for Person Re-identification
* Unsupervised Domain Attention Adaptation Network for Caricature Attribute Recognition
* Unsupervised Learning of Category-specific Symmetric 3d Keypoints from Point Sets
* Unsupervised Learning of Optical Flow with Deep Feature Similarity
* Unsupervised Monocular Depth Estimation for Night-time Images Using Adversarial Domain Feature Adaptation
* Unsupervised Multi-view CNN for Salient View Selection of 3D Objects and Scenes
* Unsupervised Shape and Pose Disentanglement for 3d Meshes
* Unsupervised Sketch to Photo Synthesis
* Unsupervised Video Object Segmentation with Joint Hotspot Tracking
* URIE: Universal Image Enhancement for Visual Recognition in the Wild
* Urvos: Unified Referring Video Object Segmentation Network with a Large-scale Benchmark
* Utilizing Patch-level Category Activation Patterns for Multiple Class Novelty Detection
* V2vnet: Vehicle-to-vehicle Communication for Joint Perception and Prediction
* Variational Connectionist Temporal Classification
* Variational Diffusion Autoencoders with Random Walk Sampling
* Varsr: Variational Super-resolution Network for Very Low Resolution Images
* Vcnet: A Robust Approach to Blind Image Inpainting
* Vectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Inference
* Video Object Detection via Object-level Temporal Aggregation
* Video Object Segmentation with Episodic Graph Memory Networks
* Video Representation Learning by Recognizing Temporal Transformations
* Video Super-resolution with Recurrent Structure-detail Network
* Video-based Remote Physiological Measurement via Cross-verified Feature Disentangling
* View-invariant Probabilistic Embedding for Human Pose
* Virtual Multi-view Fusion for 3d Semantic Segmentation
* Visual Compositional Learning for Human-object Interaction Detection
* Visual Memorability for Robotic Interestingness via Unsupervised Online Learning
* Visual Question Answering on Image Sets
* Visual Relation Grounding in Videos
* Visual-relation Conscious Image Generation from Structured-text
* Visualcomet: Reasoning About the Dynamic Context of a Still Image
* Visualechoes: Spatial Image Representation Learning Through Echolocation
* Vitaa: Visual-textual Attributes Alignment in Person Search by Natural Language
* VLANet: Video-language Alignment Network for Weakly-supervised Video Moment Retrieval
* Volumetric Transformer Networks
* Voxelpose: Towards Multi-camera 3d Human Pose Estimation in Wild Environment
* Vpn: Learning Video-Pose Embedding for Activities of Daily Living
* VQA-LOL: Visual Question Answering Under the Lens of Logic
* Wavelet-based Dual-branch Network for Image Demoiréing
* We Have So Much in Common: Modeling Semantic Relational Set Abstractions in Videos
* Weakly Supervised 3d Hand Pose Estimation via Biomechanical Constraints
* Weakly Supervised 3d Human Pose and Shape Reconstruction with Normalizing Flows
* Weakly Supervised 3d Object Detection from Lidar Point Cloud
* Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances
* Weakly Supervised Learning with Side Information for Noisy Labeled Images
* Weakly Supervised Semantic Segmentation with Boundary Exploration
* Weakly-supervised 3d Shape Completion in the Wild
* Weakly-supervised Action Localization with Expectation-maximization Multi-instance Learning
* Weakly-supervised Cell Tracking via Backward-and-forward Propagation
* Weakly-supervised Crowd Counting Learns from Sorting Rather Than Locations
* Weakly-supervised Learning of Human Dynamics
* Webly Supervised Image Classification with Self-Contained Confidence
* Weighing Counts: Sequential Crowd Counting by Reinforcement Learning
* Weight Decay Scheduling and Knowledge Distillation for Active Learning
* Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks
* WeightNet: Revisiting the Design Space of Weight Networks
* What Is Learned in Deep Uncalibrated Photometric Stereo?
* What Makes Fake Images Detectable? Understanding Properties that Generalize
* What Matters in Unsupervised Optical Flow
* When Does Self-supervision Improve Few-shot Learning?
* Where to Explore Next? Exhistcnn for History-Aware Autonomous 3D Exploration
* Who Left the Dogs Out? 3d Animal Reconstruction with Expectation Maximization in the Loop
* Whole-body Human Pose Estimation in the Wild
* Why Are Deep Representations Good Perceptual Quality Features?
* Why Do These Match? Explaining the Behavior of Image Similarity Models
* World-Consistent Video-to-Video Synthesis
* XingGAN for Person Image Generation
* Yet Another Intermediate-level Attack
* Yolo in the Dark: Domain Adaptation Method for Merging Multiple Models
* You Are Here: Geolocation by Embedding Maps and Images
* Zero-shot Image Super-resolution with Depth Guided Internal Degradation Learning
1357 for ECCV20

ECCV22 * *ECCV
* 2D Amodal Instance Segmentation Guided by 3D Shape Prior
* 2D GANs Meet Unsupervised Single-View 3D Reconstruction
* 2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
* 3D Clothed Human Reconstruction in the Wild
* 3D CoMPaT: Composition of Materials on Parts of 3D Things
* 3D Compositional Zero-Shot Learning with DeCompositional Consensus
* 3D Equivariant Graph Implicit Functions
* 3D Face Reconstruction with Dense Landmarks
* 3D Human Pose Estimation Using Möbius Graph Convolutional Networks
* 3D Instances as 1D Kernels
* 3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal
* 3D Object Detection with a Self-supervised Lidar Scene Flow Backbone
* 3D Random Occlusion and Multi-layer Projection for Deep Multi-camera Pedestrian Localization
* 3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform
* 3D Scene Inference from Transient Histograms
* 3D Shape Sequence of Human Comparison and Classification Using Current and Varifolds
* 3D Siamese Transformer Network for Single Object Tracking on Point Clouds
* 3D-Aware Indoor Scene Synthesis with Depth Priors
* 3D-Aware Semantic-Guided Generative Model for Human Synthesis
* 3D-FM GAN: Towards 3D-Controllable Face Manipulation
* 3D-PL: Domain Adaptive Depth Estimation with 3D-Aware Pseudo-Labeling
* 3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching
* 4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding
* A-OKVQA: A Benchmark for Visual Question Answering Using World Knowledge
* Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning, The
* Abstracting Sketches Through Simple Primitives
* Accelerating Score-Based Generative Models with Preconditioned Diffusion Sampling
* Accurate Detection of Proteins in Cryo-Electron Tomograms from Sparse Labels
* Acknowledging the Unknown for Multi-Label Learning with Single Positive Labels
* AcroFOD: An Adaptive Method for Cross-Domain Few-Shot Object Detection
* Action Quality Assessment with Temporal Parsing Transformer
* Action-Based Contrastive Learning for Trajectory Prediction
* ActionFormer: Localizing Moments of Actions with Transformers
* Active Audio-Visual Separation of Dynamic Sound Sources
* Active Label Correction Using Robust Parameter Update and Entropy Propagation
* Active Learning Strategies for Weakly-Supervised Object Detection
* Active Pointly-Supervised Instance Segmentation
* ActiveNeRF: Learning Where to See with Uncertainty Estimation
* Actor-Centered Representations for Action Localization in Streaming Videos
* AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-Shot Interactions
* AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation
* AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets
* AdaFocusV3: On Unified Spatial-Temporal Dynamic Video Recognition
* AdaNeRF: Adaptive Sampling for Real-Time Rendering of Neural Radiance Fields
* Adaptive Agent Transformer for Few-Shot Segmentation
* Adaptive Co-teaching for Unsupervised Monocular Depth Estimation
* Adaptive Cross-Domain Learning for Generalizable Person Re-identification
* Adaptive Face Forgery Detection in Cross Domain
* Adaptive Feature Interpolation for Low-Shot Image Generation
* Adaptive Fine-Grained Sketch-Based Image Retrieval
* Adaptive Image Transformations for Transfer-Based Adversarial Attack
* Adaptive Patch Exiting for Scalable Single Image Super-Resolution
* Adaptive Spatial-BCE Loss for Weakly Supervised Semantic Segmentation
* Adaptive Token Sampling for Efficient Vision Transformers
* Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing
* Addressing Heterogeneity in Federated Learning via Distributional Transformation
* AdvDO: Realistic Adversarial Attacks for Trajectory Prediction
* Adversarial Contrastive Learning via Asymmetric InfoNCE
* Adversarial Erasing Framework via Triplet with Gated Pyramid Pooling Layer for Weakly Supervised Semantic Segmentation
* Adversarial Feature Augmentation for Cross-domain Few-Shot Classification
* Adversarial Label Poisoning Attack on Graph Neural Networks via Label Propagation
* Adversarial Partial Domain Adaptation by Cycle Inconsistency
* Adversarially-Aware Robust Object Detector
* Affine Correspondences Between Multi-Camera Systems for 6DOF Relative Pose Estimation
* AgeTransGAN for Facial Age Transformation with Rectified Performance Metrics
* AiATrack: Attention in Attention for Transformer Visual Tracking
* AirDet: Few-Shot Detection Without Fine-Tuning for Autonomous Exploration
* AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction
* All You Need Is RAW: Defending Against Adversarial Attacks with Camera Image Pipelines
* Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks
* AlphaVC: High-Performance and Efficient Learned Video Compression
* AMixer: Adaptive Weight Mixing for Self-Attention Free Vision Transformers
* Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing, The
* Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance
* AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment
* Anti-Neuron Watermarking: Protecting Personal Data Against Unauthorized Neural Networks
* Anti-retroactive Interference for Lifelong Learning
* Any-Resolution Training for High-Resolution Image Synthesis
* Approximate Differentiable Rendering with Algebraic Surfaces
* Approximate Discrete Optimal Transport Plan with Auxiliary Measure Method
* ARAH: Animatable Volume Rendering of Articulated Human SDFs
* Are Vision Transformers Robust to Patch Perturbations?
* ARF: Artistic Radiance Fields
* ARM: Any-Time Super-Resolution Method
* ART-SS: An Adaptive Rejection Technique for Semi-Supervised Restoration for Adverse Weather-Affected Images
* ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer
* ASSISTER: Assistive Navigation via Conditional Instruction Generation
* AssistQ: Affordance-Centric Question-Driven Task Completion for Egocentric Assistant
* Asymmetric Relation Consistency Reasoning for Video Relation Grounding
* Attaining Class-Level Forgetting in Pretrained Model Using Few Samples
* Attention Diversification for Domain Generalization
* Attention-Aware Learning for Hyperparameter Prediction in Image Processing Pipelines
* AU-Aware 3D Face Reconstruction through Personalized AU-Specific Blendshape Learning
* Audio-Driven Stylized Gesture Generation with Flow-Based Model
* Audio-Visual Mismatch-Aware Video Retrieval via Association and Adjustment
* Audio-Visual Segmentation
* AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation
* Augmentation of rPPG Benchmark Datasets: Learning to Remove and Embed rPPG Signals via Double Cycle Consistent Learning from Unpaired Facial Videos
* Augmenting Deep Classifiers with Polynomial Neural Networks
* Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentation
* Auto-regressive Image Synthesis with Integrated Quantization
* AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling
* Automatic Check-Out via Prototype-Based Classifier Learning from Single-Product Exemplars
* Automatic Dense Annotation of Large-Vocabulary Sign Language Videos
* AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
* Autoregressive 3D Shape Generation via Canonical Mapping
* Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction
* AutoTransition: Learning to Recommend Video Transition Effects
* AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture
* AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing
* Aware of the History: Trajectory Forecasting with the Local Behavior Data
* BA-Net: Bridge Attention for Deep Convolutional Neural Networks
* Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
* Background-Insensitive Scene Text Recognition with Text Semantic Segmentation
* Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization
* Balancing Between Forgetting and Acquisition in Incremental Subpopulation Learning
* Balancing Stability and Plasticity Through Advanced Null Space in Continual Learning
* Bandwidth-Aware Adaptive Codec for DNN Inference Offloading in IoT
* BASQ: Branch-wise Activation-clipping Search Quantization for Sub-4-bit Neural Networks
* Batch-Efficient EigenDecomposition for Small and Medium Matrices
* BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
* BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks
* Bayesian Optimization with Clustering and Rollback for CNN Auto Pruning
* Bayesian Tracking of Video Graphs Using Joint Kalman Smoothing and Registration
* BEAT: A Large-Scale Semantic and Emotional Multi-modal Dataset for Conversational Gestures Synthesis
* Benchmarking Omni-Vision Representation Through the Lens of Visual Realms
* BEVFormer: Learning Bird's-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers
* Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs
* Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation
* Bi-level Feature Alignment for Versatile Image Translation and Manipulation
* Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation
* BigColor: Colorization Using a Generative Color Prior for Natural Images
* Bilateral Normal Integration
* BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-Aided Adversarial Learning
* Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach
* Black-Box Dissector: Towards Erasing-Based Hard-Label Model Stealing Attack
* Black-Box Few-Shot Knowledge Distillation
* Blind Image Decomposition
* BlobGAN: Spatially Disentangled Scene Representations
* BLT: Bidirectional Layout Transformer for Controllable Layout Generation
* BMD: A General Class-Balanced Multicentric Dynamic Prototype Strategy for Source-Free Domain Adaptation
* BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking
* Boosting Event Stream Super-Resolution with a Recurrent Neural Network
* Boosting Supervised Dehazing Methods via Bi-level Patch Reweighting
* Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks
* Bootstrapped Masked Autoencoders for Vision BERT Pretraining
* Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds
* BoundaryFace: A Mining Framework with Noise Label Self-correction for Face Recognition
* Box-Supervised Instance Segmentation with Level Set Evolution
* Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation using Bounding Boxes
* BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis
* Breadcrumbs: Adversarial Class-Balanced Sampling for Long-Tailed Recognition
* Break and Make: Interactive Structural Understanding Using LEGO Bricks
* Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection
* Bridging the Domain Gap Towards Generalization in Automatic Colorization
* Bridging the Visual Semantic Gap in VLN via Semantically Richer Instructions
* Bringing Rolling Shutter Images Alive with Dual Reversed Distortion
* BRNet: Exploring Comprehensive Features for Monocular Depth Estimation
* Broad Study of Pre-training for Domain Generalization and Adaptation, A
* BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering
* Burn After Reading: Online Adaptation for Cross-domain Streaming Data
* ByteTrack: Multi-object Tracking by Associating Every Detection Box
* BézierPalm: A Free Lunch for Palmprint Recognition
* C3P: Cross-Domain Pose Prior Propagation for Weakly Supervised 3D Human Pose Estimation
* CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation
* CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution
* Calibration-Free Multi-view Crowd Counting
* Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting, The
* Camera Auto-calibration from the Steiner Conic of the Fundamental Matrix
* Camera Pose Auto-encoders for Improving Pose Regression
* Camera Pose Estimation and Localization with Active Audio Sensing
* Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding
* CANF-VC: Conditional Augmented Normalizing Flows for Video Compression
* Capturing, Reconstructing, and Simulating: The UrbanScene3D Dataset
* CAR: Class-Aware Regularizations for Semantic Segmentation
* Cartoon Explanations of Image Classifiers
* Category-Level 6D Object Pose and Size Estimation Using Self-supervised Deep Prior Deformation Networks
* CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement
* CAViT: Contextual Alignment Vision Transformer for Video Object Re-identification
* CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer
* CelebV-HQ: A Large-Scale Video Facial Attributes Dataset
* CenterFormer: Center-Based Transformer for 3D Object Detection
* Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels
* Chairs Can Be Stood On: Overcoming Object Bias in Human-Object Interaction Detection
* Challenges of Continuous Self-Supervised Learning, The
* Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection
* CHORE: Contact, Human and Object Reconstruction from a Single RGB Image
* ChunkyGAN: Real Image Inversion via Segments
* CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-Scale Indoor Scene
* Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization
* Class-Agnostic Object Counting Robust to Intraclass Diversity
* Class-Agnostic Object Detection with Multi-modal Transformer
* Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer
* Class-Incremental Novel Class Discovery
* Classification-Regression for Chart Comprehension
* CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition
* ClearPose: Large-scale Transparent Object Dataset and Benchmark
* CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation
* CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes
* CLOSE: Curriculum Learning on the Sharing Extent Towards Better One-Shot NAS
* Closer Look at Invariances in Self-supervised Pre-training for 3D Vision, A
* Cloud 3D Dataset and Application-Specific Learned Image Compression in Cloud 3D, A
* CMD: Self-supervised 3D Action Representation Learning with Cross-Modal Mutual Distillation
* CMT: Context-Matching-Guided Transformer for 3D Tracking in Point Clouds
* Coarse-To-Fine Incremental Few-Shot Learning
* Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction
* CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving
* Codec Information Assisted Framework for Efficient Compressed Video Super-Resolution, A
* CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval
* CoGS: Controllable Generation and Search from Sketch and Style
* Collaborating Domain-Shared and Target-Specific Feature Clustering for Cross-domain 3D Action Recognition
* ColorFormer: Image Colorization via Color Memory Assisted Hybrid-Attention Transformer
* Colorization for in situ Marine Plankton Images
* Combating Label Distribution Shift for Active Domain Adaptation
* Combining Internal and External Constraints for Unrolling Shutter in Videos
* CoMER: Modeling Coverage for Transformer-Based Handwritten Mathematical Expression Recognition
* Comparative Study of Graph Matching Algorithms in Computer Vision, A
* Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
* Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction
* Completely Self-supervised Crowd Counting via Distribution Matching
* CompNVS: Novel View Synthesis with Scene Completion
* COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality
* Compositional Human-Scene Interaction Synthesis with Semantic Control
* Compositional Visual Generation with Composable Diffusion Models
* Compound Prototype Matching for Few-Shot Action Recognition
* ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology Images
* Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation
* Conditional Stroke Recovery for Fine-Grained Sketch-Based Image Retrieval
* Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantification
* ConMatch: Semi-supervised Learning with Confidence-Guided Consistency Regularization
* Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search
* Constrained Mean Shift Using Distant yet Related Neighbors for Representation Learning
* Constructing Balance from Imbalance for Long-Tailed Image Recognition
* Content Adaptive Latents and Decoder for Neural Image Compression
* Content-Oriented Learned Image Compression
* Context-Aware Streaming Perception in Dynamic Environments
* Context-Consistent Semantic Image Editing with Style-Preserved Modulation
* Context-Enhanced Stereo Transformer
* Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression
* Contextual Text Block Detection Towards Scene Text Understanding
* Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
* Continual Semantic Segmentation via Structure Preserving and Projected Feature Alignment
* Continual Variational Autoencoder Learning via Online Cooperative Memorization
* Contrast-Phys: Unsupervised Video-Based Remote Physiological Measurement via Spatiotemporal Contrast
* Contrasting Quadratic Assignments for Set-Based Representation Learning
* Contrastive Deep Supervision
* Contrastive Learning for Diverse Disentangled Foreground Generation
* Contrastive Monotonic Pixel-Level Modulation
* Contrastive Objective for Learning Disentangled Representations, A
* Contrastive Positive Mining for Unsupervised 3D Action Representation Learning
* Contrastive Prototypical Network with Wasserstein Confidence Penalty
* Contrastive Vicinal Space for Unsupervised Domain Adaptation
* Contrastive Vision-Language Pre-training with Limited Resources
* Contributions of Shape, Texture, and Color in Visual Recognition
* Controllable and Guided Face Synthesis for Unconstrained Face Recognition
* Controllable Shadow Generation Using Pixel Height Maps
* Controllable Video Generation Through Global and Local Motion Dynamics
* Convolutional Embedding Makes Hierarchical Vision Transformer Stronger
* COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
* Cornerformer: Purifying Instances for Corner-Based Detectors
* Correspondence Reweighted Translation Averaging
* CoSCL: Cooperation of Small Continual Learners is Stronger Than a Big One
* CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation
* Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
* CostDCNet: Cost Volume Based Depth Completion for a Single RGB-D Image
* COUCH: Towards Controllable Human-Chair Interactions
* Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
* CoupleFace: Relation Matters for Face Recognition Distillation
* CoVisPose: Co-visibility Pose Transformer for Wide-Baseline Relative Pose Estimation in 360° Indoor Panoramas
* CP 2: Copy-Paste Contrastive Pretraining for Semantic Segmentation
* CPO: Change Robust Panorama to Point Cloud Localization
* CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution
* CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection
* Cross Attention Based Style Distribution for Controllable Person Image Synthesis
* Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers
* Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations
* Cross-domain Ensemble Distillation for Domain Generalization
* Cross-Domain Few-Shot Semantic Segmentation
* Cross-modal 3D Shape Generation and Manipulation
* Cross-Modal Knowledge Transfer Without Task-Relevant Source Data
* Cross-Modal Prototype Driven Network for Radiology Report Generation
* Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection
* Cross-Modality Transformer for Visible-Infrared Person Re-Identification
* CryoAI: Amortized Inference of Poses for Ab Initio Reconstruction of 3D Molecular Volumes from Real Cryo-EM Images
* CT2: Colorization Transformer via Color Tokens
* Custom Structure Preservation in Face Aging
* CXR Segmentation by AdaIN-Based Domain Adaptation and Knowledge Distillation
* CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation
* CycDA: Unsupervised Cycle Domain Adaptation to Learn from Image to Video
* D 3 Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding
* D&D: Learning Human Dynamics from Dynamic Camera
* D2-TPred: Discontinuous Dependency for Trajectory Prediction Under Traffic Lights
* D2ADA: Dynamic Density-Aware Active Domain Adaptation for Semantic Segmentation
* D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution
* D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration
* DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks
* DAS: Densely-Anchored Sampling for Deep Metric Learning
* Data Association Between Event Streams and Intensity Frames Under Diverse Baselines
* Data Efficient 3D Learner via Knowledge Transferred from 2D Model
* Data Invariants to Understand Unsupervised Out-of-Distribution Detection
* Data-Centric Approach for Improving Ambiguous Labels with Combined Semi-supervised Classification and Clustering, A
* Data-Free Backdoor Removal Based on Channel Lipschitzness
* Data-Free Neural Architecture Search via Recursive Label Calibration
* Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility, A
* Dataset Generation Framework for Evaluating Megapixel Image Classifiers and Their Explanations, A
* DaViT: Dual Attention Vision Transformers
* DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization
* DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
* DeciWatch: A Simple Baseline for 10× Efficient 2D and 3D Pose Estimationo
* Decomposing the Tangent of Occluding Boundaries According to Curvatures and Torsions
* Decouple-and-Sample: Protecting Sensitive Information in Task Agnostic Data Release
* Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness
* Decoupled Contrastive Learning
* DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation
* Deep 360° Optical Flow Estimation Based on Multi-projection Fusion
* Deep Bayesian Video Frame Interpolation
* Deep Ensemble Learning by Diverse Knowledge Distillation for Fine-Grained Object Classification
* Deep Fourier-Based Exposure Correction Network with Spatial-Frequency Interaction
* Deep Hash Distillation for Image Retrieval
* Deep Moving-Camera Background Model, A
* Deep Partial Updating: Towards Communication Efficient Updating for On-Device Inference
* Deep Portrait Delighting
* Deep Radial Embedding for Visual Sequence Learning
* Deep Semantic Statistics Matching (D2SM) Denoising Network
* DeepMend: Learning Occupancy Functions to Represent Shape for Repair
* DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images
* DeepShadow: Neural Shape from Shadow
* Deformable Feature Aggregation for Dynamic Multi-modal 3D Object Detection
* Deforming Radiance Fields with Cages
* DeiT III: Revenge of the ViT
* Delta Distillation for Efficient Video Processing
* DeltaGAN: Towards Diverse Few-Shot Image Generation with Sample-Specific Delta
* DELTAR: Depth Estimation from a Light-Weight ToF Sensor and RGB Image
* Delving into Details: Synopsis-to-Detail Networks for Video Recognition
* Delving into Universal Lesion Segmentation: Method, Dataset, and Benchmark
* DeMFI: Deep Joint Deblurring and Multi-frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting
* Demystifying Unsupervised Semantic Correspondence Estimation
* Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
* Dense Gaussian Processes for Few-Shot Segmentation
* Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing, A
* Dense Siamese Network for Dense Unsupervised Learning
* Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection
* DenseHybrid: Hybrid Anomaly Detection for Dense Open-Set Recognition
* Densely Constrained Depth Estimator for Monocular 3D Object Detection
* Depth Field Networks For Generalizable Multi-View Scene Representation
* Depth Map Decomposition for Monocular Depth Estimation
* Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping
* Detecting and Recovering Sequential DeepFake Manipulation
* Detecting Generated Images by Real Images
* Detecting Tampered Scene Text in the Wild
* Detecting Twenty-Thousand Classes Using Image-Level Supervision
* DetMatch: Two Teachers are Better than One for Joint 2D and 3D Semi-Supervised Object Detection
* DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection
* DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction
* DexMV: Imitation Learning for Dexterous Manipulation from Human Videos
* DFNet: Enhance Absolute Pose Regression with Direct Feature Matching
* DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose Estimation
* DICE: Leveraging Sparsification for Out-of-Distribution Detection
* DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection
* DiffConv: Analyzing Irregular Point Clouds with an Irregular View
* Differentiable Raycasting for Self-Supervised Occupancy Forecasting
* Differentiable Zooming for Multiple Instance Learning on Whole-Slide Images
* Difficulty-Aware Simulator for Open Set Recognition
* DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model
* DiffuStereo: High Quality Human Reconstruction via Diffusion-Based Stereo Using Sparse Cameras
* Digging into Radiance Grid for Real-Time View Synthesis with Detail Preservation
* Directed Ray Distance Functions for 3D Scene Reconstruction
* DisCo: Remedying Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning
* Discover and Mitigate Unknown Biases with Debiasing Alternate Networks
* Discovering Deformable Keypoint Pyramids
* Discovering Human-Object Interaction Concepts via Self-Compositional Learning
* Discovering Transferable Forensic Features for CNN-Generated Images Detection
* Discrete-Constrained Regression for Local Counting Models
* Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective
* Disentangled Differentiable Network Pruning
* Disentangling Architecture and Training for Optical Flow
* Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth
* DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation
* Distilling Object Detectors with Global Knowledge
* Distilling the Undistillable: Learning from a Nasty Teacher
* DistPro: Searching a Fast Knowledge Distillation Process via Meta Optimization
* Diverse Generation from a Single Video Made Possible
* Diverse Human Motion Prediction Guided by Multi-level Spatial-Temporal Anchors
* Diverse Image Inpainting with Normalizing Flow
* Diverse Learner: Exploring Diverse Supervision for Semi-supervised Object Detection
* DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning
* DLME: Deep Local-Flatness Manifold Embedding
* DnA: Improving Few-Shot Transfer Learning with Low-Rank Decomposition and Alignment
* DODA: Data-Oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation
* Domain Adaptive Hand Keypoint and Pixel Localization in the Wild
* Domain Adaptive Person Search
* Domain Adaptive Video Segmentation via Temporal Pseudo Supervision
* Domain Generalization by Mutual-Information Regularization with Pre-trained Models
* Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains
* Domain Knowledge-Informed Self-supervised Representations for Workout Form Assessment
* Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
* Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context
* DoodleFormer: Creative Sketch Drawing with Transformers
* Doubly Deformable Aggregation of Covariance Matrices for Few-Shot Segmentation
* Doubly-Fused ViT: Fuse Information from Vision Transformer Doubly with Local Representation
* DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimation
* DRCNet: Dynamic Image Restoration Contrastive Network
* Dress Code: High-Resolution Multi-category Virtual Try-On
* Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation
* DSR: A Dual Subspace Re-Projection Network for Surface Anomaly Detection
* Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation
* Dual Contrastive Learning with Anatomical Auxiliary Supervision for Few-Shot Medical Image Segmentation
* Dual Perspective Network for Audio-Visual Event Localization
* Dual-Domain Self-supervised Learning and Model Adaption for Deep Compressive Imaging
* Dual-Evidential Learning for Weakly-supervised Temporal Action Localization
* Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval
* DualFormer: Local-Global Stratified Transformer for Efficient Video Recognition
* DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning
* DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training
* DVS-Voltmeter: Stochastic Process-Based Event Simulator for Dynamic Vision Sensors
* Dynamic 3D Scene Analysis by Point Cloud Accumulation
* Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
* Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection
* Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting
* Dynamic Metric Learning with Cross-Level Concept Distillation
* Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition
* Dynamic Temporal Filtering in Video Models
* Dynamically Transformed Instance Normalization Network for Generalizable Person Re-Identification
* DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation
* E-Graph: Minimal Solution for Rigid Rotation with Extensibility Graphs
* E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context
* EAGAN: Efficient Two-Stage Evolutionary Architecture Search for GANs
* EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching
* EAutoDet: Efficient Architecture Search for Object Detection
* ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO
* EclipSE: Efficient Long-Range Video Retrieval Using Sight and Sound
* ECO-TR: Efficient Correspondences Finding via Coarse-to-Fine Refinement
* EdgeViTs: Competing Light-Weight CNNs on Mobile Devices with Vision Transformers
* Editable Indoor Lighting Estimation
* Editing Out-of-Domain GAN Inversion via Differential Activations
* Effective Presentation Attack Detection Driven by Face Related Task
* Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution
* Efficient Decoder-Free Object Detection with Transformers
* Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection
* Efficient Long-Range Attention Network for Image Super-Resolution
* Efficient Meta-Tuning for Content-Aware Neural Video Delivery
* Efficient One Pass Self-distillation with Zipf's Label Smoothing
* Efficient One-Stage Video Object Detection by Exploiting Temporal Consistency
* Efficient Person Clustering Algorithm for Open Checkout-free Groceries, An
* Efficient Point Cloud Analysis Using Hilbert Curve
* Efficient Point Cloud Segmentation with Geometry-Aware Sparse Networks
* Efficient Spatio-Temporal Pyramid Transformer for Action Detection, An
* Efficient Video Deblurring Guided by Motion Magnitude
* Efficient Video Transformers with Spatial-Temporal Token Selection
* EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices
* Egocentric Activity Recognition and Localization on a 3D Map
* EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer
* Eliminating Gradient Conflict in Reference-based Line-Art Colorization
* Embedded Feature Whitening Approach to Deep Neural Network Optimization, An
* Embedding Contrastive Unsupervised Features to Cluster In- And Out-of-Distribution Noise in Corrupted Image Datasets
* Emotion Recognition for Multiple Context Awareness
* Emotion-aware Multi-view Contrastive Learning for Facial Emotion Recognition
* End-to-End Active Speaker Detection
* End-to-End Graph-Constrained Vectorized Floorplan Generation with Panoptic Refinement
* End-to-End Transformer Model for Crowd Localization, An
* End-to-End Visual Editing with a Generatively Pre-Trained Artist
* End-to-End Weakly Supervised Object Detection with Sparse Proposal Evolution
* Enhanced Accuracy and Robustness via Multi-teacher Adversarial Distillation
* Enhancing Multi-modal Features Using Local Self-attention for 3D Object Detection
* Ensemble Knowledge Guided Sub-network Search and Fine-Tuning for Filter Pruning
* Ensemble Learning Priors Driven Deep Unfolding for Scalable Video Snapshot Compressive Imaging
* Entropy-Driven Sampling and Training Scheme for Conditional Diffusion Generation
* Entry-Flipped Transformer for Inference and Prediction of Participant Behavior
* Equivariance and Invariance Inductive Bias for Learning from Insufficient Data
* Equivariant Hypergraph Neural Networks
* ERA: Enhanced Rational Activations
* ERA: Expert Retrieval and Assembly for Early Action Prediction
* ERDN: Equivalent Receptive Field Deformable Network for Video Deblurring
* Error Compensation Framework for Flow-Guided Video Inpainting
* ESS: Learning Event-Based Semantic Segmentation from Still Images
* Estimating Spatially-Varying Lighting in Urban Scenes with Disentangled Representation
* EvAC3D: From Event-Based Apparent Contours to 3D Models via Continuous Visual Hulls
* Event Neural Networks
* Event-Based Fusion for Motion Deblurring with Cross-modal Attention
* Event-guided Deblurring of Unknown Exposure Time Videos
* Expanded Adaptive Scaling Normalization for End to End Image Compression
* Expanding Language-Image Pretrained Models for General Video Recognition
* Explaining Deepfake Detection by Analysing Image Matching
* Explicit Image Caption Editing
* Explicit Model Size Control and Relaxation via Smooth Regularization for Mixed-Precision Quantization
* Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation
* Exploiting the Local Parabolic Landscapes of Adversarial Losses to Accelerate Black-Box Adversarial Attack
* Exploiting Unlabeled Data with Vision and Language Models for Object Detection
* Exploring Disentangled Content Information for Face Forgery Detection
* Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset
* Exploring Gradient-Based Multi-directional Controls in GANs
* Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification
* Exploring Lottery Ticket Hypothesis in Spiking Neural Networks
* Exploring Plain Vision Transformer Backbones for Object Detection
* Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection
* Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks
* Exposure-Aware Dynamic Weighted Learning for Single-Shot HDR Imaging
* Extract Free Dense Labels from CLIP
* ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing
* Fabric Material Recovery from Video Using Multi-scale Geometric Auto-Encoder
* Face2Face-rho: Real-Time High-Resolution One-Shot Face Reenactment
* Facial Depth and Normal Estimation Using Single Dual-Pixel Camera
* Factorizing Knowledge in Neural Networks
* FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling
* FairGRAPE: Fairness-Aware GRAdient Pruning mEthod for Face Attribute Classification
* FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations
* FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs
* FAR: Fourier Aerial Video Recognition
* Fashionformer: A Simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition
* FashionViL: Fashion-Focused Vision-and-Language Representation Learning
* Fast and High Quality Image Denoising via Malleable Convolution
* Fast Knowledge Distillation Framework for Visual Recognition, A
* Fast Two-Step Blind Optical Aberration Correction
* Fast Two-View Motion Segmentation Using Christoffel Polynomials
* Fast-MoCo: Boost Momentum-Based Contrastive Learning with Combinatorial Patches
* Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis
* FAST-VQA: Efficient End-to-End Video Quality Assessment with Fragment Sampling
* Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection
* FBNet: Feedback Network for Point Cloud Completion
* FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection
* FEAR: Fast, Efficient, Accurate and Robust Visual Tracker
* Feature Representation Learning for Unsupervised Cross-Domain Image Retrieval
* Federated Self-supervised Learning for Video Understanding
* FedLTN: Federated Learning for Sparse and Personalized Lottery Ticket Networks
* FedVLN: Privacy-Preserving Federated Vision-and-Language Navigation
* FedX: Unsupervised Federated Learning with Cross Knowledge Distillation
* Few Zero Level Set-Shot Learning of Shape Signed Distance Functions in Feature Space
* Few-Shot Action Recognition with Hierarchical Matching and Contrastive Learning
* Few-Shot Class-Incremental Learning for 3D Point Cloud Objects
* Few-Shot Class-Incremental Learning from an Open-Set Perspective
* Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay
* Few-Shot Classification with Contrastive Learning
* Few-Shot End-to-End Object Detection via Constantly Concentrated Encoding Across Heads
* Few-Shot Image Generation with Mixup-Based Distance Learning
* Few-Shot Object Counting and Detection
* Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations
* Few-Shot Object Detection with Model Calibration
* Few-Shot Single-View 3D Reconstruction with Memory Prior Contrastive Network
* Few-Shot Video Object Detection
* FH-Net: A Fast Hierarchical Network for Scene Flow Estimation on Real-World Point Clouds
* FILM: Frame Interpolation for Large Motion
* Filter Pruning via Feature Discrimination in Deep Neural Networks
* FindIt: Generalized Localization with Natural Language Queries
* Fine-grained Data Distribution Alignment for Post-Training Quantization
* Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications
* Fine-Grained Fashion Representation Learning by Online Deep Clustering
* Fine-Grained Scene Graph Generation with Data Transfer
* Fine-Grained Visual Entailment
* FingerprintNet: Synthesized Fingerprints for Generated Image Detection
* FLEX: Extrinsic Parameters-free Multi-View 3D Human Motion Reconstruction
* FloatingFusion: Depth from ToF and Image-Stabilized Stereo Cameras
* Flow Graph to Video Grounding for Weakly-Supervised Multi-step Localization
* Flow-Guided Transformer for Video Inpainting
* FlowFormer: A Transformer Architecture for Optical Flow
* FOSTER: Feature Boosting and Compression for Class-Incremental Learning
* Free-Viewpoint RGB-D Human Performance Capture and Rendering
* Frequency and Spatial Dual Guidance for Image Dehazing
* Frequency Domain Model Augmentation for Adversarial Attack
* FrequencyLowCut Pooling: Plug and Play Against Catastrophic Overfitting
* From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution
* Frozen CLIP Models are Efficient Video Learners
* FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context
* FurryGAN: High Quality Foreground-Aware Image Synthesis
* Fusing Local Similarities for Retrieval-Based 3D Orientation Estimation of Unseen Objects
* Fusion from Decomposition: A Self-Supervised Decomposition Approach for Image Fusion
* FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion
* GaitEdge: Beyond Plain End-to-End Gait Recognition for Better Practicality
* GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing
* GAMa: Cross-View Video Geo-Localization
* GAN Cocktail: Mixing GANs Without Dataset Access
* GAN with Multivariate Disentangling for Controllable Hair Editing
* Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction and Pose Estimation
* GCISG: Guided Causal Invariant Learning for Improved Syn-to-Real Generalization
* GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval
* Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images
* General Object Pose Transformation Network from Unpaired Data
* Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration
* Generalizable Patch-Based Neural Rendering
* Generalized and Robust Framework for Timestamp Supervision in Temporal Action Segmentation, A
* Generalized Brain Image Synthesis with Transferable Convolutional Sparse Coding Networks
* Generating Natural Images with Direct Patch Distributions Matching
* Generative Adversarial Network for Future Hand Segmentation from Egocentric Video
* Generative Domain Adaptation for Face Anti-Spoofing
* Generative Meta-Adversarial Network for Unseen Object Navigation
* Generative Multiplane Images: Making a 2D GAN 3D-Aware
* Generative Negative Text Replay for Continual Vision-Language Pretraining
* Generative Subgraph Contrast for Self-Supervised Graph Representation Learning
* Generator Knows What Discriminator Should Learn in Unconditional GANs
* GeoAug: Data Augmentation for Few-Shot NeRF with Geometry Constraints
* Geodesic-Former: A Geodesic-Guided Few-Shot 3D Point Cloud Instance Segmenter
* Geometric Features Informed Multi-person Human-Object Interaction Recognition in Videos
* Geometric Representation Learning for Document Image Rectification
* Geometry-Aware Single-Image Full-Body Human Relighting
* Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering
* GeoRefine: Self-supervised Online Depth Refinement for Accurate Dense Mapping
* Ghost-free High Dynamic Range Imaging with Context-Aware Transformer
* GigaDepth: Learning Depth from Structured Light with Branching Neural Networks
* GIMO: Gaze-Informed Human Motion Prediction in Context
* GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation
* GitNet: Geometric Prior-Based Transformation for Birds-Eye-View Segmentation
* GLAMD: Global and Local Attention Mask Distillation for Object Detectors
* GLASS: Global to Local Attention for Scene-Text Spotting
* Global Spectral Filter Memory Network for Video Object Segmentation
* Global-Local Motion Transformer for Unsupervised Skeleton-Based Action Learning
* GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning
* GradAuto: Energy-Oriented Attack on Dynamic Neural Networks
* Gradient-Based Uncertainty for Monocular Depth Estimation
* Granularity-Aware Adaptation for Image Retrieval Over Multiple Tasks
* Graph Neural Network for Cell Tracking in Microscopy Videos
* Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph
* Graph-Constrained Contrastive Regularization for Semi-weakly Volumetric Segmentation
* GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs
* GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation
* GraphVid: It only Takes a Few Nodes to Understand a Video
* Grasp'D: Differentiable Contact-Rich Grasp Synthesis for Multi-Fingered Hands
* GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training
* GRIT: Faster and Better Image Captioning Transformer Using Dual Visual Features
* Grounding Visual Representations with Texts for Domain Generalization
* GTCaR: Graph Transformer for Camera Re-localization
* Gyrovector Space Approach for Symmetric Positive Semi-definite Matrix Learning, A
* HairNet: Hairstyle Transfer with Pose Changes
* Hallucinating Pose-Compatible Scenes
* Hardly Perceptible Trojan Attack Against Neural Networks with Bit Flips
* Harmonizer: Learning to Perform White-Box Image and Video Harmonization
* HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields
* HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors
* Helpful or Harmful: Inter-task Association in Continual Learning
* Hierarchical Average Precision Training for Pertinent Image Retrieval
* Hierarchical Contrastive Inconsistency Learning for Deepfake Video Detection
* Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation
* Hierarchical Feature Embedding for Visual Tracking
* Hierarchical Latent Structure for Multi-modal Vehicle Trajectory Forecasting
* Hierarchical Memory Learning for Fine-Grained Scene Graph Generation
* Hierarchical Semantic Regularization of Latent Spaces in StyleGANs
* Hierarchical Semi-supervised Contrastive Learning for Contamination-Resistant Anomaly Detection
* Hierarchically Self-supervised Transformer for Human Skeleton Representation Learning
* High-Fidelity GAN Inversion with Padding Space
* High-Fidelity Image Inpainting with GAN Inversion
* High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions
* Highly Accurate Dichotomous Image Segmentation
* HIVE: Evaluating the Human Interpretability of Visual Explanations
* HM: Hybrid Masking for Few-Shot Segmentation
* Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection
* Hourglass Attention Network for Image Inpainting
* Housekeep: Tidying Virtual Households Using Commonsense Reasoning
* How Severe Is Benchmark-Sensitivity in Video Self-Supervised Learning?
* How Stable Are Transferability Metrics Evaluations?
* How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?
* HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation
* HULC: 3D HUman Motion Capture with Pose Manifold SampLing and Dense Contact Guidance
* Human Trajectory Prediction via Neural Social Physics
* Human-Centric Image Cropping with Partition-Aware and Content-Preserving Features
* HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling
* Hunting Group Clues with Transformers for Social Group Activity Recognition
* HVC-Net: Unifying Homography, Visibility, and Confidence Learning for Planar Object Tracking
* Hyperspherical Learning in Multi-Label Classification
* IDa-Det: An Information Discrepancy-Aware Distillation for 1-Bit Detectors
* Identifying Hard Noise in Long-Tailed Sample Distribution
* Identity-Aware Hand Mesh Estimation and Personalization from RGB Images
* IGFormer: Interaction Graph Transformer for Skeleton-Based Human Interaction Recognition
* Image Coding for Machines with Omnipotent Feature Learning
* Image Inpainting with Cascaded Modulation GAN and Object-Aware Training
* Image Super-Resolution with Deep Dictionary
* Image-Based CLIP-Guided Essence Transfer
* Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models
* Impartial Take to the CNN vs Transformer Robustness Contest, An
* Implicit Field Supervision for Robust Non-rigid Shape Matching
* Implicit Neural Representations for Image Compression
* Implicit Neural Representations for Variable Length Human Motion Generation
* Improved Masked Image Generation with Token-Critic
* Improving Adversarial Robustness of 3D Point Cloud Classification Models
* Improving Closed and Open-Vocabulary Attribute Prediction Using Transformers
* Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality
* Improving Few-Shot Learning Through Multi-task Representation Learning Theory
* Improving Few-Shot Part Segmentation Using Coarse Supervision
* Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-boosting Attention Mechanism
* Improving GANs for Long-Tailed Data Through Group Spectral Regularization
* Improving Generalization in Federated Learning by Seeking Flat Minima
* Improving Image Restoration by Revisiting Global Information Aggregation
* Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation
* Improving Robustness by Enhancing Weak Subnets
* Improving Self-supervised Lightweight Model Learning via Hard-Aware Metric Distillation
* Improving Test-Time Adaptation Via Shift-Agnostic Weight Regularization and Nearest Source Prototypes
* Improving the Intra-class Long-Tail in 3D Detection via Rare Example Mining
* Improving the Perceptual Quality of 2D Animation Interpolation
* Improving the Reliability for Confidence Estimation
* Improving Vision Transformers by Revisiting High-Frequency Components
* In Defense of Image Pre-Training for Spatiotemporal Recognition
* In Defense of Online Models for Video Instance Segmentation
* InAction: Interpretable Action Decision Making for Autonomous Driving
* incDFM: Incremental Deep Feature Modeling for Continual Novelty Detection
* Incomplete Multi-view Domain Adaptation via Channel Enhancement and Knowledge Transfer
* Incremental Task Learning with Incremental Rank Updates
* Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments
* InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images
* Information Theoretic Approach for Attention-Driven Face Forgery Detection, An
* Initialization and Alignment for Adversarial Texture Optimization
* Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis
* Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-curation
* Instance as Identity: A Generic Online Paradigm for Video Instance Segmentation
* Instance Contour Adjustment via Structure-Driven CNN
* INT: Towards Infinite-Frames 3D Detection with an Efficient Framework
* IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-View Human Reconstruction
* Intelli-Paint: Towards Developing More Human-Intelligible Painting Agents
* Interclass Prototype Relation for Few-Shot Segmentation
* IntereStyle: Encoding an Interest Region for Robust StyleGAN Inversion
* Interpretable Image Classification with Differentiable Prototypes Assignment
* Interpretable Open-Set Domain Adaptation via Angular Margin Separation
* Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps
* Intrinsic Neural Fields: Learning Functions on Manifolds
* Invariant Feature Learning for Generalized Long-Tailed Classification
* Inverted Pyramid Multi-task Transformer for Dense Scene Understanding
* Invisible Black-Box Backdoor Attack Through Frequency Domain, An
* Is Appearance Free Action Recognition Possible?
* Is Geometry Enough for Matching in Visual Localization?
* Is It Necessary to Transfer Temporal Knowledge for Domain Adaptive Video Semantic Segmentation?
* IS-MVSNet:Importance Sampling-Based MVSNet
* Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows
* Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
* Joint Learning of Localized Representations from Medical Images and Reports
* Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing
* JoJoGAN: One Shot Face Stylization
* JPEG Artifacts Removal via Contrastive Representation Learning
* JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes
* K-centered Patch Sampling for Efficient Video Recognition
* k-means Mask Transformer
* k-SALSA: k-Anonymous Synthetic Averaging of Retinal Images via Local Style Alignment
* KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-View Stereo
* Kendall Shape Space Approach to 3D Shape Estimation from 2D Landmarks, A
* Kernel Relative-prototype Spectral Filtering for Few-Shot Learning
* KeypointNeRF: Generalizing Image-Based Volumetric Avatars Using Relative Spatial Encoding of Keypoints
* KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients
* Knowledge Condensation Distillation
* KVT: k-NN Attention for Boosting Vision Transformers
* KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution
* L-CoDer: Language-Based Colorization with Color-Object Decoupling Transformer
* L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing
* L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training
* l8-Robustness and Beyond: Unleashing Efficient Adversarial Training
* LA3: Efficient Label-Aware AutoAugment
* Label-Guided Auxiliary Training Improves 3D Object Detector
* Label2Label: A Language Modeling Framework for Multi-attribute Learning
* LaLaLoc++: Global Floor Plan Comprehension for Layout Localisation in Unvisited Environments
* LaMAR: Benchmarking Localization and Mapping for Augmented Reality
* LANA: Latency Aware Network Acceleration
* Lane Detection Transformer Based on Multi-frame Horizontal and Vertical Attention and Visual Transformer Module
* Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting
* Language-Driven Artistic Style Transfer
* Language-Grounded Indoor 3D Semantic Segmentation in the Wild
* Laplacian Mesh Transformer: Dual Attention and Topology Aware Network for 3D Mesh Classification and Segmentation
* Large Scale Real-World Multi-person Tracking
* Large-Displacement 3D Object Tracking with Hybrid Non-local Optimization
* Large-Scale Multiple-Objective Method for Black-box Attack Against Object Detection, A
* Latency-Aware Collaborative Perception
* Latent Discriminant Deterministic Uncertainty
* Latent Partition Implicit with Surface Codes for 3D Representation
* Latent Space Smoothing for Individually Fair Representations
* LaTeRF: Label and Text Driven Object Radiance Fields
* Layered Controllable Video Generation
* Learn from All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition
* Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition
* Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition
* Learned Monocular Depth Priors in Visual-Inertial Initialization
* Learned Variational Video Color Propagation
* Learned Vertex Descent: A New Direction for 3D Human Model Fitting
* Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning
* Learning an Isometric Surface Parameterization for Texture Unwrapping
* Learning Audio-Video Modalities from Image Captions
* Learning Continuous Implicit Representation for Near-Periodic Patterns
* Learning Cross-Video Neural Representations for High-Quality Frame Interpolation
* Learning Deep Non-blind Image Deconvolution Without Ground Truths
* Learning Degradation Representations for Image Deblurring
* Learning Depth from Focus in the Wild
* Learning Discriminative Shrinkage Deep Networks for Image Deconvolution
* Learning Disentanglement with Decoupled Labels for Vision-Language Navigation
* Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis
* Learning Efficient Multi-Agent Cooperative Visual Exploration
* Learning Ego 3D Representation as Ray Tracing
* Learning Energy-Based Models with Adversarial Training
* Learning Extremely Lightweight and Robust Model with Differentiable Constraints on Sparsity and Condition Number
* Learning from Multiple Annotator Noisy Labels via Sample-Wise Label Fusion
* Learning from Unlabeled 3D Environments for Vision-and-Language Navigation
* Learning Graph Neural Networks for Image Style Transfer
* Learning Hierarchy Aware Features for Reducing Mistake Severity
* Learning Implicit Feature Alignment Function for Semantic Segmentation
* Learning Implicit Templates for Point-Based Clothed Human Modeling
* Learning Instance and Task-Aware Dynamic Kernels for Few-Shot Learning
* Learning Instance-Specific Adaptation for Cross-Domain Segmentation
* Learning Invariant Visual Representations for Compositional Zero-Shot Learning
* Learning Linguistic Association Towards Efficient Text-Video Retrieval
* Learning Local Implicit Fourier Representation for Image Warping
* Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection
* Learning Mutual Modulation for Self-supervised Cross-Modal Super-Resolution
* Learning Object Placement via Dual-Path Graph Completion
* Learning Omnidirectional Flow in 360° Video via Siamese Representation
* Learning Online Multi-Sensor Depth Fusion
* Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction
* Learning Phase Mask for Privacy-Preserving Passive Depth Estimation
* Learning Prior Feature and Attention Enhanced Image Inpainting
* Learning Quality-aware Dynamic Memory for Video Object Segmentation
* Learning Regional Purity for Instance Segmentation on 3D Point Clouds
* Learning Self-prior for Mesh Denoising Using Dual Graph Convolutional Networks
* Learning Semantic Correspondence with Sparse Annotations
* Learning Semantic Segmentation from Multiple Datasets with Label Shifts
* Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution
* Learning Shadow Correspondence for Video Shadow Detection
* Learning Spatial-Preserved Skeleton Representations for Few-Shot Action Recognition
* Learning Spatio-Temporal Downsampling for Effective Video Upscaling
* Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution
* Learning to Censor by Noisy Sampling
* Learning to Detect Every Thing in an Open World
* Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining
* Learning to Fit Morphable Models
* Learning to Generate Realistic LiDAR Point Clouds
* Learning to Learn with Smooth Regularization
* Learning to Train a Point Cloud Reconstruction Network Without Matching
* Learning to Weight Samples for Dynamic Early-Exiting Networks
* Learning Topological Interactions for Multi-Class Medical Image Segmentation
* Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling
* Learning Uncoupled-Modulation CVAE for 3D Action-Conditioned Human Motion Synthesis
* Learning Visibility for Robust Dense Human Body Estimation
* Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training
* Learning Visual Styles from Audio-Visual Associations
* Learning Where to Look: Generative NAS is Surprisingly Efficient
* Learning with Free Object Segments for Long-Tailed Instance Segmentation
* Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection
* Learning with Recoverable Forgetting
* Learning-Based Point Cloud Registration for 6D Object Pose Estimation in the Real World
* LEDNet: Joint Low-Light Enhancement and Deblurring in the Dark
* Less Than Few: Self-shot Video Instance Segmentation
* LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds
* Level Set Theory for Neural Implicit Evolution Under Explicit Flows, A
* Levenshtein OCR
* Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentation
* LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity
* LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation
* LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection
* Lidar Point Cloud Guided Monocular 3D Object Detection
* LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds
* Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval
* LiP-Flow: Learning Inference-Time Priors for Codec Avatars via Normalizing Flows in Latent Space
* Lipschitz Continuity Retained Binary Neural Network
* Local Color Distributions Prior for Image Enhancement
* LocalBins: Improving Depth Estimation by Learning Local Distributions
* Locality Guidance for Improving Vision Transformers on Tiny Datasets
* Localizing Visual Sounds the Easy Way
* Locally Varying Distance Transform for Unsupervised Visual Anomaly Detection
* LocVTP: Video-Text Pre-training for Temporal Localization
* Long Movie Clip Classification with State-Space Video Models
* Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
* Long-tail Detection with Effective Class-Margins
* Long-Tailed Class Incremental Learning
* Long-Tailed Instance Segmentation Using Gumbel Optimized Loss
* Look Both Ways: Self-supervising Driver Gaze Estimation and Road Scene Saliency
* LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling
* LWGNet: Learned Wirtinger Gradients for Fourier Ptychographic Phase Retrieval
* MaCLR: Motion-Aware Contrastive Learning of Representations for Videos
* Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors
* Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals
* Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing
* ManiFest: Manifold Deformation for Few-Shot Image Translation
* Manifold Adversarial Learning for Cross-Domain 3D Shape Representation
* Map-Free Visual Relocalization: Metric Pose Relative to a Single Image
* Masked Autoencoders for Point Cloud Self-Supervised Learning
* Masked Discrimination for Self-supervised Learning on Point Clouds
* Masked Generative Distillation
* Masked Siamese Networks for Label-Efficient Learning
* Master of All: Simultaneous Generalization of Urban-Scene Segmentation to All Adverse Weather Conditions
* Max Pooling with Vision Transformers Reconciles Class and Shape in Weakly Supervised Semantic Segmentation
* Max-Flow Based Approach for Neural Architecture Search, A
* MaxViT: Multi-axis Vision Transformer
* mc-BEiT: Multi-choice Discretization for Image BERT Pre-training
* Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation
* MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment
* Memory-Augmented Model-Driven Network for Pansharpening
* MemSAC: Memory Augmented Sample Consistency for Large Scale Domain Adaptation
* MENet: A Memory-Based Network with Dual-Branch for Efficient Event Stream Processing
* MeshLoc: Mesh-Based Visual Localization
* MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis
* MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks
* Meta Spatio-Temporal Debiasing for Video Scene Graph Generation
* Meta-GF: Training Dynamic-Depth Neural Networks Harmoniously
* Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions
* Meta-sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds
* MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition
* Metric Learning Based Interactive Modulation for Real-World Super-Resolution
* MFIM: Megapixel Facial Identity Manipulation
* MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views
* MILES: Visual BERT Pre-training with Injected Language Semantics for Video-Text Retrieval
* MIME: Minority Inclusion for Majority Group Enhancement of AI Performance
* Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification
* MimicME: A Large Scale Diverse 4D Database for Facial Expression Analysis
* Mind the Gap in Distilling StyleGANs
* MINER: Multiscale Implicit Neural Representation
* Minimal Neural Atlas: Parameterizing Complex Surfaces with Minimal Charts and Distortion
* Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection
* Mining Relations Among Cross-Frame Affinities for Video Semantic Segmentation
* Missing Link: Finding Label Relations Across Datasets, The
* Mixed-Precision Neural Network Quantization via Learned Layer-Wise Importance
* MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition
* ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation
* MoDA: Map Style Transfer for Self-supervised Domain Adaptation of Embodied Agents
* Modality Synergy Complement Learning with Cascaded Aggregation for Visible-Infrared Person Re-Identification
* MODE: Multi-view Omnidirectional Depth Estimation with 360° Cameras
* Modeling Mask Uncertainty in Hyperspectral Image Reconstruction
* MoFaNeRF: Morphable Facial Neural Radiance Field
* Monitored Distillation for Positive Congruent Depth Completion
* Monocular 3D Object Detection with Depth from Motion
* Monocular 3D Object Reconstruction with GAN Inversion
* MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene Flow Estimation with Monocular Images
* MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud
* MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes
* MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning
* Most and Least Retrievable Images in Visual-Language Query Systems
* MOTCOM: The Multi-Object Tracking Dataset Complexity Metric
* Motion and Appearance Adaptation for Cross-domain Motion Transfer
* Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving
* Motion Sensitive Contrastive Learning for Self-Supervised Video Representation
* Motion Transformer for Unsupervised Image Animation
* MotionCLIP: Exposing Human Motion Generation to CLIP Space
* MOTR: End-to-End Multiple-Object Tracking with Transformer
* MovieCuts: A New Dataset and Benchmark for Cut Type Recognition
* MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects
* MPPNet: Multi-frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
* MTFormer: Multi-task Learning via Transformer and Cross-Task Reasoning
* MTTrans: Cross-domain Object Detection with Mean Teacher Transformer
* MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration
* Multi-Curve Translator for High-Resolution Photorealistic Image Translation
* Multi-domain Learning for Updating Face Anti-spoofing Models
* Multi-domain Multi-definition Landmark Localization for Small Datasets
* Multi-Exit Semantic Segmentation Networks
* Multi-faceted Distillation of Base-Novel Commonality for Few-Shot Object Detection
* Multi-granularity Distillation Scheme Towards Lightweight Semi-supervised Semantic Segmentation
* Multi-granularity Prediction for Scene Text Recognition
* Multi-granularity Pruning for Model Acceleration on Mobile Devices
* Multi-modal Masked Pre-training for Monocular Panoramic Depth Completion
* Multi-modal Text Recognition Networks: Interactive Enhancements Between Visual and Semantic Features
* Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement
* Multi-Query Video Retrieval
* Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation
* MultiMAE: Multi-modal Multi-task Masked Autoencoders
* Multimodal Conditional Image Synthesis with Product-of-Experts GANs
* Multimodal Object Detection via Probabilistic Ensembling
* Multimodal Transformer for Automatic 3D Annotation and Object Detection
* Multimodal Transformer with Variable-Length Memory for Vision-and-Language Navigation
* Multiview Regenerative Morphing with Dual Flows
* Multiview Stereo with Cascaded Epipolar RAFT
* MuLUT: Cooperating Multiple Look-Up Tables for Efficient Image Super-Resolution
* Mutually Reinforcing Structure with Proposal Contrastive Consistency for Few-Shot Object Detection
* MvDeCor: Multi-view Dense Correspondence Learning for Fine-Grained 3D Segmentation
* MVDG: A Unified Multi-view Framework for Domain Generalization
* MVP: Multimodality-Guided Visual Pre-training
* MVSalNet: Multi-view Augmentation for RGB-D Salient Object Detection
* MVSTER: Epipolar Transformer for Efficient Multi-view Stereo
* My View is the Best View: Procedure Learning from Egocentric Videos
* NashAE: Disentangling Representations Through Adversarial Covariance Minimization
* Natural Synthetic Anomalies for Self-supervised Anomaly Detection and Localization
* NDF: Neural Deformable Fields for Dynamic Human Modelling
* NeFSAC: Neurally Filtered Minimal Samples
* Negative Samples are at Large: Leveraging Hard-Distance Elastic Loss for Re-identification
* Neighborhood Collective Estimation for Noisy Label Identification and Chiorrection
* NeILF: Neural Incident Light Field for Physically-based Material Estimation
* NeRF for Outdoor Scene Relighting
* NEST: Neural Event Stack for Event-Based Image Enhancement
* Network Binarization via Contrastive Learning
* NeuMan: Neural Human Radiance Field from a Single Video
* NeuMesh: Learning Disentangled Neural Mesh-Based Implicit Field for Geometry and Texture Editing
* Neural Architecture Search for Spiking Neural Networks
* Neural Capture of Animatable 3D Human from Monocular Video
* Neural Color Operators for Sequential Image Retouching
* Neural Correspondence Field for Object Pose Estimation
* Neural Density-Distance Fields
* Neural Image Representations for Multi-Image Fusion and Layer Separation
* Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion
* Neural Radiance Transfer Fields for Relightable Novel-View Synthesis with Global Illumination
* Neural Scene Decoration from a Single Photograph
* Neural Space-Filling Curves
* Neural Strands: Learning Hair Geometry and Appearance from Multi-view Images
* Neural Video Compression Using GANs for Detail Synthesis and Propagation
* Neural-Sim: Learning to Generate Training Data with NeRF
* NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors
* Neuromorphic Data Augmentation for Training Spiking Neural Networks
* New Datasets and Models for Contextual Reasoning in Visual Dialog
* NewsStories: Illustrating Articles with Visual Summaries
* NeXT: Towards High Quality Neural Radiance Fields via Multi-skip Transformer
* No Token Left Behind: Explainability-Aided Image Classification and Generation
* Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning, A
* Non-uniform Step Size Quantization for Accurate Post-training Quantization
* Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space
* Not Just Streaks: Towards Ground Truth for Single Image Deraining
* Novel Class Discovery Without Forgetting
* NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition
* NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion
* Object Detection as Probabilistic Set Prediction
* Object Discovery and Representation Networks
* Object Discovery via Contrastive Learning for Weakly Supervised Object Detection
* Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation from Monocular RGB Image
* Object Manipulation via Visual Target Localization
* Object Wake-Up: 3D Object Rigging from a Single Image
* Object-Centric Unsupervised Image Captioning
* Object-Compositional Neural Implicit Surfaces
* ObjectBox: From Centers to Boxes for Anchor-Free Object Detection
* Objects Can Move: 3D Change Detection by Geometric Transformation Consistency
* OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses
* OCR-Free Document Understanding Transformer
* OIMNet++: Prototypical Normalization and Localization-Aware Learning for Person Search
* On Label Granularity and Object Localization
* On Mitigating Hard Clusters for Face Clustering
* On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond
* On the Angular Update and Hyperparameter Tuning of a Scale-Invariant Network
* On the Robustness of Quality Measures for GANs
* On the Versatile Uses of Partial Distance Correlation in Deep Learning
* One Size Does NOT Fit All: Data-Adaptive Adversarial Training
* One Where They Reconstructed 3D Humans and Environments in TV Shows, The
* One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement
* One-Trimap Video Matting
* OneFace: One Threshold for All
* Online Continual Learning with Contrastive Vision Transformer
* Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions
* Online Segmentation of LiDAR Sequences: Dataset and Algorithm
* Online Task-free Continual Learning with Dynamic Sparse Distributed Memory
* OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images
* OPD: Single-View 3D Openable Part Detection
* Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
* Open-Set Semi-Supervised Object Detection
* Open-Vocabulary DETR with Conditional Matching
* Open-world Semantic Segmentation for LIDAR Point Clouds
* Open-World Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding
* OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning
* Optical Flow Training Under Limited Label Budget via Active Learning
* Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning
* Optimal Transport for Label-Efficient Visible-Infrared Person Re-Identification
* Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation
* Optimizing Image Compression via Joint Learning with Denoising
* Order Learning Using Partially Ordered Data via Chainization
* Organic Priors in Non-rigid Structure from Motion
* OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers
* Out-of-distribution Detection with Boundary Aware Learning
* Out-of-Distribution Detection with Semantic Mismatch Under Masking
* Out-of-Distribution Identification: Let Detector Tell Which I Am Not Sure
* Outpainting by Queries
* Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain
* Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction
* P-STMO: Pre-trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation
* PAC-Net: Highlight Your Video via History Preference Modeling
* PACS: A Dataset for Physical Audiovisual CommonSense Reasoning
* PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks
* Paint2Pix: Interactive Painting Based Progressive Image Synthesis and Editing
* Pairwise Contrastive Learning Network for Action Quality Assessment
* PalGAN: Image Colorization with Palette Generative Adversarial Networks
* PalQuant: Accelerating High-Precision Networks on Low-Precision Accelerators
* PANDORA: A Panoramic Detection Dataset for Object with Orientation
* PANDORA: Polarization-Aided Neural Decomposition of Radiance
* PanoFormer: Panorama Transformer for Indoor 360 ° Depth Estimation
* Panoptic Scene Graph Generation
* Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation
* Panoramic Human Activity Recognition
* Panoramic Vision Transformer for Saliency Detection in 360° Videos
* Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration
* ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer
* Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories
* ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild
* PartImageNet: A Large, High-Quality Dataset of Parts
* PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification
* Patch Similarity Aware Data-Free Quantization for Vision Transformers
* PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation
* PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry
* PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching
* PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows
* Perceiving and Modeling Density for Image Dehazing
* Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution
* Perceptual Artifacts Localization for Inpainting
* Perceptual Quality Metric for Video Frame Interpolation, A
* PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
* Personalized Education: Blind Knowledge Distillation
* Personalizing Federated Medical Image Segmentation via Local Calibration
* Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation
* Perspective Phase Angle Model for Polarimetric 3D Reconstruction
* Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow, A
* PETR: Position Embedding Transformation for Multi-View 3D Object Detection
* Photo-realistic Neural Domain Randomization
* Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
* Physically-Based Editing of Indoor Scene Lighting from a Single Image
* PillarNet: Real-Time and High-Performance Pillar-Based 3D Object Detection
* PIP: Physical Interaction Prediction via Mental Simulation with Span Selection
* Pixel-Wise Energy-Biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes
* PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation
* PlaneFormers: From Sparse View Planes to 3D Reconstruction
* Planes vs. Chairs: Category-Guided 3D Shape Learning Without any 3D Cues
* Point Cloud Compression with Range Image-Based Entropy Model for Autonomous Driving
* Point Cloud Compression with Sibling Context and Surface Priors
* Point Cloud Domain Adaptation via Masked Local 3D Structure Prediction
* Point MixSwap: Attentional Point Cloud Mixing via Swapping Matched Structural Divisions
* Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding
* Point Scene Understanding via Disentangled Instance Mesh Reconstruction
* Point-to-Box Network for Accurate Object Detection via Single Point Supervision
* PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registration
* PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
* PointInst3D: Segmenting 3D Instances by Points
* Pointly-Supervised Panoptic Segmentation
* PointMixer: MLP-Mixer for Point Cloud Understanding
* PointScatter: Point Set Representation for Tubular Structure Extraction
* PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees
* Polarimetric Pose Prediction
* PolarMOT: How Far Can Geometric Relations Take us in 3D Multi-object Tracking?
* PolyphonicFormer: Unified Query Learning for Depth-Aware Video Panoptic Segmentation
* POP: Mining POtential Performance of New Fashion Products via Webly Cross-modal Query Expansion
* Pose for Everything: Towards Category-Agnostic Pose Estimation
* Pose Forecasting in Industrial Human-Robot Collaboration
* Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields
* Pose2Room: Understanding 3D Scenes from Human Activities
* PoseGPT: Quantization-Based 3D Human Motion Generation and Forecasting
* PoserNet: Refining Relative Camera Poses Exploiting Object Detections
* PoseScript: 3D Human Poses from Natural Language
* PoseTrans: A Simple yet Effective Pose Transformation Augmentation for Human Pose Estimation
* Poseur: Direct Human Pose Regression with Transformers
* Posterior Refinement on Metric Matrix Improves Generalization Bound in Metric Learning
* PPT: Token-Pruned Pose Transformer for Monocular and Multi-view Human Pose Estimation
* Practical and Scalable Desktop-Based High-Quality Facial Capture
* Pre-training Strategies and Datasets for Facial Representation Learning
* Predicting Is Not Understanding: Recognizing and Addressing Underspecification in Machine Learning
* Prediction-Guided Distillation for Dense Object Detection
* PREF: Predictability Regularized Neural Motion Fields
* PressureVision: Estimating Hand Pressure from a Single RGB Image
* PreTraM: Self-supervised Pre-training via Connecting Trajectory and Map
* PRIF: Primary Ray-Based Implicit Function
* PRIME: A Few Primitives Can Boost Robustness to Common Corruptions
* Primitive-Based Shape Abstraction via Nonparametric Bayesian Inference
* Prior Knowledge Guided Unsupervised Domain Adaptation
* Prior-Guided Adversarial Initialization for Fast Adversarial Training
* Privacy-Preserving Action Recognition via Motion Difference Quantization
* Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain
* PrivHAR: Recognizing Human Actions from Privacy-Preserving Lens
* Projective Parallel Single-Pixel Imaging to Overcome Global Illumination in 3D Structure Light Scanning
* PromptDet: Towards Open-Vocabulary Detection Using Uncurated Images
* Prompting Visual-Language Models for Efficient Video Understanding
* Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning
* ProposalContrast: Unsupervised Pre-training for LiDAR-Based 3D Object Detection
* Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation
* Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation
* Prune Your Model Before Distill It
* PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo
* PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection
* PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds
* PseudoClick: Interactive Image Segmentation with Click Imitation
* PSS: Progressive Sample Selection for Open-World Visual Representation Learning
* PT4AL: Using Self-supervised Pretext Tasks for Active Learning
* PTQ4ViT: Post-training Quantization for Vision Transformers with Twin Uniform Quantization
* PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection
* Pure Transformer with Integrated Experts for Scene Text Recognition
* Q-FW: A Hybrid Classical-Quantum Frank-Wolfe for Quadratic Binary Optimization
* QISTA-ImageNet: A Deep Compressive Image Sensing Framework Solving Lq-Norm Optimization Problem
* Quantized GAN for Complex Music Generation from Dance Videos
* Quantum Motion Segmentation
* Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap
* R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning
* R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis
* RA-Depth: Resolution Adaptive Self-supervised Monocular Depth Estimation
* Radatron: Accurate Detection Using Multi-resolution Cascaded MIMO Radar
* RadioTransformer: A Cascaded Global-Focal Transformer for Visual Attention-Guided Disease Classification
* RamGAN: Region Attentive Morphing GAN for Region-Level Makeup Transfer
* RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation
* RAWtoBit: A Fully End-to-end Camera ISP Network
* Rayleigh EigenDirections (REDs): Nonlinear GAN Latent Space Traversals for Multidimensional Features
* RayTran: 3D Pose Estimation and Shape Reconstruction of Multiple Objects from Videos with Ray-Traced Transformers
* RBC: Rectifying the Biased Context in Continual Semantic Segmentation
* RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation
* RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering
* RCLane: Relay Chain Prediction for Lane Detection
* RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learning
* RDO-Q: Extremely Fine-Grained Channel-Wise Quantization via Rate-Distortion Optimization
* ReAct: Temporal Action Detection with Relational Queries
* Real Spike: Learning Real-Valued Spikes for Spiking Neural Networks
* Real World Dataset for Multi-view 3D Reconstruction, A
* Real-RawVSR: Real-World Raw Video Super-Resolution with a Benchmark Dataset
* Real-Time Intermediate Flow Estimation for Video Frame Interpolation
* Real-Time Neural Character Rendering with Pose-Guided Multiplane Images
* Real-Time Online Video Detection with Temporal Smoothing Transformers
* RealFlow: EM-Based Realistic Optical Flow Dataset Generation from Videos
* Realistic Blur Synthesis for Learning Image Deblurring
* Realistic One-Shot Mesh-Based Head Avatars
* RealPatch: A Statistical Matching Framework for Model Patching with Real Samples
* REALY: Rethinking the Evaluation of 3D Face Reconstruction
* ReCoNet: Recurrent Correction Network for Fast and Efficient Multi-modality Image Fusion
* Recover Fair Deep Classification Models via Altering Pre-trained Structure
* Recurrent Bilinear Optimization for Binary Neural Networks
* Reducing Information Loss for Spiking Neural Networks
* Reference-Based Image Super-Resolution with Deformable Attention Transformer
* Referring Object Manipulation of Natural Images with Conditional Classifier-Free Guidance
* RegionCL: Exploring Contrastive Region Pairs for Self-supervised Representation Learning
* Registration Based Few-Shot Anomaly Detection
* Regularizing Vector Embedding in Bottom-Up Human Pose Estimation
* Relationformer: A Unified Framework for Image-to-Graph Generation
* Relationship Spatialization for Depth Estimation
* Relative Contrastive Loss for Unsupervised Representation Learning
* Relative Pose from SIFT Features
* Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval
* Reliable Online Method for Joint Estimation of Focal Length and Camera Rotation, A
* Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly
* Relighting4D: Neural Relightable Human from Videos
* RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild
* Remote Respiration Monitoring of Moving Person Using Radio Signals
* RepMix: Representation Mixing for Robust Attribution of Synthesized Images
* Repulsive Force Unit for Garment Collision Handling in Neural Networks, A
* Resolution-Free Point Cloud Sampling Network with Data Distillation
* Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction
* Responsive Listening Head Generation: A Benchmark Dataset and Baseline
* Restore Globally, Refine Locally: A Mask-Guided Scheme to Accelerate Super-Resolution Networks
* Rethinking Closed-Loop Training for Autonomous Driving
* Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning
* Rethinking Confidence Calibration for Failure Prediction
* Rethinking Data Augmentation for Robust Visual Question Answering
* Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark
* Rethinking Generic Camera Models for Deep Single Image Camera Calibration to Recover Rotation and Fisheye Distortion
* Rethinking IoU-based Optimization for Single-stage 3D Object Detection
* Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-person Human Pose Estimation
* Rethinking Learning Approaches for Long-Term Action Anticipation
* Rethinking Robust Representation Learning Under Fine-Grained Noisy Faces
* Rethinking Video Rain Streak Removal: A New Synthesis Model and a Deraining Network with Video Rain Prior
* Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions
* Revisiting a kNN-Based Image Classification System with High-Capacity Storage
* Revisiting Batch Norm Initialization
* Revisiting Outer Optimization in Adversarial Training
* Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach
* Revisiting the Critical Factors of Augmentation-Invariant Representation Learning
* RFLA: Gaussian Receptive Field Based Label Assignment for Tiny Object Detection
* RFNet-4D: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds
* RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN
* RigNet: Repetitive Image Guided Network for Depth Completion
* Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features
* Robust Landmark-Based Stent Tracking in X-ray Fluoroscopy
* Robust Multi-object Tracking by Marginal Inference
* Robust Network Architecture Search via Feature Distortion Restraining
* Robust Object Detection with Inaccurate Bounding Boxes
* Robust Visual Tracking by Segmentation
* Rotation Regularization Without Rotation
* RRSR: Reciprocal Reference-Based Image Super-Resolution with Progressive Feature Alignment and Selection
* RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-supervised Learning
* S 2 Contact: Graph-Based Network for 3D Hand-Object Contact Estimation with Semi-supervised Learning
* S2-VER: Semi-supervised Visual Emotion Recognition
* S2F2: Single-Stage Flow Forecasting for Future Multiple Trajectories Prediction
* S2N: Suppression-Strengthen Network for Event-Based Recognition Under Variant Illuminations
* S2Net: Stochastic Sequential Pointcloud Forecasting
* S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning
* SAFA: Sample-Adaptive Feature Augmentation for Long-Tailed Image Classification
* SAGA: Stochastic Whole-Body Grasping with Contact
* Saliency Hierarchy Modeling via Generative Kernels for Salient Object Detection
* Salient Object Detection for Point Clouds
* SALISA: Saliency-Based Input Sampling for Efficient Video Object Detection
* SALVe: Semantic Alignment Verification for Floorplan Reconstruction from Sparse Panoramas
* SAU: Smooth Activation Function Using Convolution with Approximate Identities
* SC-wLS: Towards Interpretable Feed-forward Camera Re-localization
* Scalable Learning to Optimize: A Learned Optimizer Can Train Big Models
* ScalableViT: Rethinking the Context-Oriented Generalization of Vision Transformer
* Scale-Aware Spatio-Temporal Relation Learning for Video Anomaly Detection
* ScaleNet: Searching for the Model to Scale
* Scaling Adversarial Training to Large Perturbation Bounds
* Scaling Open-Vocabulary Image Segmentation with Image-Level Labels
* SCAM! Transferring Humans Between Images with Semantic Cross Attention Modulation
* Scene Text Recognition with Permuted Autoregressive Sequence Models
* Scraping Textures from Natural Images for Synthesis and Editing
* SdAE: Self-distillated Masked Autoencoder
* SecretGen: Privacy Recovery on Pre-trained Models via Distribution Discrimination
* Secrets of Event-Based Optical Flow
* SeedFormer: Patch Seeds Based Point Cloud Completion with Upsample Transformer
* Seeing Far in the Dark with Patterned Flash
* Seeing Through a Black Box: Toward High-Quality Terahertz Imaging via Subspace-and-Attention Guided Restoration
* SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness
* Selection and Cross Similarity for Event-Image Deep Stereo
* SelectionConv: Convolutional Neural Networks for Non-rectilinear Image Data
* Selective Query-Guided Debiasing for Video Corpus Moment Retrieval
* Selective TransHDR: Transformer-Based Selective HDR Imaging Using Ghost Region Mask
* Self-calibrating Photometric Stereo by Neural Inverse Rendering
* Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation
* Self-Distillation for Robust LiDAR Semantic Segmentation in Autonomous Driving
* Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation
* Self-Feature Distillation with Uncertainty Modeling for Degraded Image Recognition
* Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization
* Self-Promoted Supervision for Few-Shot Transformer
* Self-Regulated Feature Learning via Teacher-free Feature Distillation
* Self-slimmed Vision Transformer
* Self-Supervised Classification Network
* Self-supervised Human Mesh Recovery with Cross-Representation Alignment
* Self-supervised Interactive Object Segmentation Through a Singulation-and-Grasping Approach
* Self-supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations
* Self-supervised Learning of Visual Graph Matching
* Self-supervised Social Relation Representation for Human Group Detection
* Self-supervised Sparse Representation for Video Anomaly Detection
* Self-Supervision Can Be a Good Few-Shot Learner
* Self-support Few-Shot Semantic Segmentation
* Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields
* Semantic Novelty Detection via Relational Reasoning
* Semantic-Aware Fine-Grained Correspondence
* Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation
* Semantic-Guided Multi-mask Image Harmonization
* Semantic-Sparse Colorization Network for Deep Exemplar-Based Colorization
* SemAug: Semantically Meaningful Image Augmentations for Object Detection Through Language Grounding
* Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning
* Semi-supervised 3D Object Detection with Proficient Teachers
* Semi-supervised Keypoint Detector and Descriptor for Retinal Image Matching
* Semi-supervised Learning of Optical Flow by Flow Supervisor
* Semi-supervised Monocular 3D Object Detection by Multi-view Consistency
* Semi-supervised Object Detection via VC Learning
* Semi-supervised Single-View 3D Reconstruction via Prototype Shape Priors
* Semi-supervised Temporal Action Detection with Proposal-Free Masking
* Semi-supervised Vision Transformers
* SEMICON: A Learning-to-Hash Solution for Large-Scale Fine-Grained Image Retrieval
* Semidefinite Relaxations of Truncated Least-Squares in Robust Rotation Search: Tight or Not
* SepLUT: Separable Image-Adaptive Lookup Tables for Real-Time Image Enhancement
* SeqFormer: Sequential Transformer for Video Instance Segmentation
* SeqTR: A Simple Yet Universal Network for Visual Grounding
* Sequential Multi-view Fusion Network for Fast LiDAR Point Motion Estimation
* SESS: Saliency Enhancing with Scaling and Sliding
* SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition
* Shap-CAM: Visual Explanations for Convolutional Neural Networks Based on Shapley Value
* Shape Matters: Deformable Patch Attack
* Shape Part Slot Machine: Contact-Based Reasoning for Generating 3D Shapes from Parts, The
* Shape-Pose Disentanglement Using SE(3)-Equivariant Vector Neurons
* ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization
* Share with Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency
* Shift-Tolerant Perceptual Similarity Metric
* Should All Proposals Be Treated Equally in Object Detection?
* SiamDoGe: Domain Generalizable Semantic Segmentation Using Siamese Network
* Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments
* Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking
* SimCC: A Simple Coordinate Classification Perspective for Human Pose Estimation
* Simple and Robust Correlation Filtering Method for Text-Based Person Search, A
* Simple Approach and Benchmark for 21,000-Category Object Detection, A
* Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-Language Model, A
* Simple Baselines for Image Restoration
* Simple Open-Vocabulary Object Detection
* Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation, A
* SimpleRecon: 3D Reconstruction Without 3D Convolutions
* Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and a New Physics-Inspired Transformer Model
* Single Stage Virtual Try-On Via Deformable Attention Flows
* Single-Stream Multi-level Alignment for Vision-Language Pretraining
* SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image
* SiRi: A Simple Selective Retraining Mechanism for Transformer-Based Visual Grounding
* Skeleton-Free Pose Transfer for Stylized 3D Characters
* Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction
* Sketch is Worth a Thousand Words: Image Retrieval with Text and Sketch, A
* SketchSampler: Sketch-Based 3D Reconstruction via View-Dependent Depth Sampling
* Sliced Recursive Transformer
* SLiDE: Self-supervised LiDAR De-snowing Through Reconstruction Difficulty
* Sliding Window Scheme for Online Temporal Action Localization, A
* Slim Scissors: Segmenting Thin Object from Synthetic Background
* SLIP: Self-supervision Meets Language-Image Pre-training
* SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos
* SNeS: Learning Probably Symmetric Neural Surfaces from Incomplete Data
* Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives
* Social ODE: Multi-agent Trajectory Forecasting with Neural Ordinary Differential Equations
* Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation
* Social-SSL: Self-supervised Cross-Sequence Representation Learning Based on Transformers for Multi-agent Trajectory Prediction
* SocialVAE: Human Trajectory Prediction Using Timewise Latents
* Soft Masking for Cost-Constrained Channel Pruning
* Solution Space Analysis of Essential Matrix Based on Algebraic Error Minimization
* SOS! Self-supervised Learning over Sets of Handled Objects in Egocentric Action Recognition
* Sound Localization by Self-supervised Time Delay Estimation
* Sound-Guided Semantic Video Generation
* Source-Free Domain Adaptation with Contrastive Domain Alignment and Self-supervised Exploration for Face Anti-spoofing
* Source-Free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition
* SP-Net: Slowly Progressing Dynamic Inference Networks
* Space-Partitioning RANSAC
* SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views
* Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding
* Spatial-Frequency Domain Information Integration for Pan-Sharpening
* Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
* SpatialDETR: Robust Scalable Transformer-Based 3D Object Detection From Multi-view Camera Images With Global Cross-Sensor Attention
* Spatially Invariant Unsupervised 3D Object-Centric Learning and Scene Decomposition
* Spatio-Temporal Deformable Attention Network for Video Deblurring
* Spatiotemporal Self-Attention Modeling with Temporal Patch Shift for Action Recognition
* SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement
* Speaker-Adaptive Lip Reading with User-Dependent Padding
* Spectral View of Randomized Smoothing Under Common Corruptions: Benchmarking and Improving Certified Robustness, A
* Spectrum-Aware and Transferable Architecture Search for Hyperspectral Image Restoration
* SphereFed: Hyperspherical Federated Learning
* Spike Transformer: Monocular Depth Estimation for Spiking Camera
* SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks
* Sports Video Analysis on Large-Scale Data
* SPot-the-Difference Self-supervised Pre-training for Anomaly Detection and Segmentation
* SpOT: Spatiotemporal Modeling for 3D Object Tracking
* Spotting Temporally Precise, Fine-Grained Events in Video
* SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection
* SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning
* SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds
* SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling
* ST-P3: End-to-End Vision-Based Autonomous Driving via Spatial-Temporal Feature Learning
* StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning
* Static and Dynamic Concepts for Self-Supervised Video Representation Learning
* STEEX: Steering Counterfactual Explanations with Semantics
* Stereo Depth Estimation with Echoes
* Stochastic Consensus: Enhancing Semi-Supervised Learning with Consistency of Stochastic Classifiers
* StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation
* Streamable Neural Fields
* Streaming Multiscale Deep Equilibrium Models
* StretchBEV: Stretching Future Instance Prediction Spatially and Temporally
* Stripformer: Strip Transformer for Fast Image Deblurring
* Structural Causal 3D Reconstruction
* Structural Triangulation: A Closed-Form Solution to Constrained 3D Human Pose Estimation
* Structure and Motion from Casual Videos
* Structure-Aware Editable Morphable Model for 3D Facial Detail Animation and Manipulation
* Studying Bias in GANs Through the Lens of Race
* Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment
* Style-Agnostic Reinforcement Learning
* Style-Based GAN Encoder for High Fidelity Reconstruction of Images and Videos, A
* Style-Guided Shadow Removal
* Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation
* StyleBabel: Artistic Style Tagging and Captioning
* StyleFace: Towards Identity-Disentangled Face Generation on Megapixels
* StyleGAN-Human: A Data-Centric Odyssey of Human Generation
* StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
* StyleLight: HDR Panorama Generation for Lighting Estimation and Editing
* StyleSwap: Style-Based Generator Empowers Robust Face Swapping
* Subspace Diffusion Generative Models
* Super-Resolution 3D Human Shape from a Single Low-Resolution Image
* Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images
* SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud
* SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning
* Supervised Attribute Information Removal and Reconstruction for Image Manipulation
* SUPR: A Sparse Unified Part-Based Human Representation
* Surprisingly Straightforward Scene Text Removal Method with Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis, The
* SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds
* Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input
* Switchable Online Knowledge Distillation
* Symmetry Regularization and Saturating Nonlinearity for Robust Quantization
* Synergistic Self-supervised and Quantization Learning
* Synthesizing Light Field Video from Monocular Video
* Tackling Background Distraction in Video Object Segmentation
* Tackling Long-Tailed Category Distribution Under Domain Shifts
* TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation
* TAFIM: Targeted Adversarial Attacks Against Facial Image Manipulations
* Tailoring Self-Supervision for Supervised Learning
* Talisman: Targeted Active Learning for Object Detection with Rare Classes and Slices Using Submodular Mutual Information
* TallFormer: Temporal Action Localization with a Long-Memory Transformer
* TAPE: Task-Agnostic Prior Embedding for Image Restoration
* Target-Absent Human Attention
* TAVA: Template-free Animatable Volumetric Actors
* TD-Road: Top-Down Road Network Extraction with Holistic Graph Construction
* TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs
* TDViT: Temporal Dilated Video Transformer for Dense Video Tasks
* Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition
* Teaching with Soft Label Smoothing for Mitigating Noisy Labels in Facial Expressions
* Telepresence Video Quality Assessment
* TEMOS: Generating Diverse Human Motions from Textual Descriptions
* TempFormer: Temporally Consistent Transformer for Video Denoising
* Temporal and Cross-modal Attention for Audio-Visual Zero-Shot Learning
* Temporal Lift Pooling for Continuous Sign Language Recognition
* Temporal Saliency Query Network for Efficient Video Recognition
* Temporal-MPI: Enabling Multi-plane Images for Dynamic Scene Modelling via Temporal Basis Learning
* Temporally Consistent Semantic Video Editing
* TensoRF: Tensorial Radiance Fields
* Text-Based Temporal Localization of Novel Events
* Text2LIVE: Text-Driven Layered Image and Video Editing
* TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers
* Texturify: Generating Textures on 3D Shape Surfaces
* Theoretical Understanding of the Information Flow on Continual Learning Performance
* This Is My Unicorn, Fluffy: Personalizing Frozen Vision-Language Representations
* Three Things Everyone Should Know About Vision Transformers
* TIDEE: Tidying Up Novel Rooms Using Visuo-Semantic Commonsense Priors
* Time-rEversed DiffusioN tEnsor Transformer: A New TENET of Few-Shot Object Detection
* TinyViT: Fast Pretraining Distillation for Small Vision Transformers
* Tip-Adapter: Training-Free Adaption of CLIP for Few-Shot Classification
* TIPS: Text-Induced Pose Synthesis
* TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation
* TL;DW? Summarizing Instructional Videos with Task Relevance and Cross-Modal Saliency
* TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
* TO-Scene: A Large-Scale Dataset for Understanding 3D Tabletop Scenes
* TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement
* TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers
* Tomography of Turbulence Strength Based on Scintillation Imaging
* Totems: Physical Objects for Verifying Visual Integrity
* Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition
* Towards Accurate Active Camera Localization
* Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies
* Towards Accurate Network Quantization with Equivalent Smooth Regularizer
* Towards Accurate Open-Set Recognition via Background-Class Regularization
* Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-Tailed Learning
* Towards Comprehensive Representation Enhancement in Semantics-Guided Self-supervised Monocular Depth Estimation
* Towards Data-Efficient Detection Transformers
* Towards Effective and Robust Neural Trojan Defenses via Input Filtering
* Towards Efficient Adversarial Training on Vision Transformers
* Towards Efficient and Effective Self-supervised Learning of Visual Representations
* Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoiréing
* Towards Generic 3D Tracking in RGBD Videos: Benchmark and Baseline
* Towards Grand Unification of Object Tracking
* Towards Hard-Positive Query Mining for DETR-Based Human-Object Interaction Detection
* Towards High-Fidelity Single-View Holistic Reconstruction of Indoor Scenes
* Towards Interpretable Video Super-Resolution via Alternating Optimization
* Towards Learning Neural Representations from Shadows
* Towards Metrical Reconstruction of Human Faces
* Towards Open Set Video Anomaly Detection
* Towards Open-Vocabulary Scene Graph Generation with Prompt-Based Finetuning
* Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation
* Towards Real-World HDRTV Reconstruction: A Data Synthesis-Based Approach
* Towards Realistic Semi-supervised Learning
* Towards Regression-Free Neural Networks for Diverse Compute Platforms
* Towards Robust Face Recognition with Comprehensive Search
* Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics
* Towards Sequence-Level Training for Visual Tracking
* Towards Ultra Low Latency Spiking Neural Networks for Vision and Sequential Tasks Using Temporal Pruning
* Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian
* Trace Controlled Text to Image Generation
* Tracking by Associating Clips
* Tracking Every Thing in the Wild
* Tracking Objects as Pixel-Wise Distributions
* Trading Positional Complexity vs Deepness in Coordinate Networks
* Training Vision Transformers with only 2040 Images
* Transfer Without Forgetting
* TransFGU: A Top-Down Approach to Fine-Grained Unsupervised Semantic Segmentation
* Transform Your Smartphone into a DSLR Camera: Learning the ISP in the Wild
* Transformer with Implicit Edges for Particle-Based Physics Simulation
* Transformer-Based Decoder for Semantic Segmentation with Multi-level Context Mining, A
* Transformers as Meta-learners for Implicit Neural Representations
* TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance
* Translating a Visual LEGO Manual to a Machine-Executable Plan
* Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection
* TransMatting: Enhancing Transparent Objects Matting with Transformers
* TransVLAD: Focusing on Locally Aggregated Descriptors for Few-Shot Learning
* Trapped in Texture Bias? A Large Scale Comparison of Deep Instance Segmentation
* Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation
* TREND: Truncated Generalized Normal Density Estimation of Inception Embeddings for GAN Evaluation
* Triangle Attack: A Query-Efficient Decision-Based Adversarial Attack
* TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments
* Trust, but Verify: Using Self-supervised Probing to Improve Trustworthiness
* TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval
* tSF: Transformer-Based Semantic Filter for Few-Shot Learning
* U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search
* UC-OWOD: Unknown-Classified Open World Object Detection
* UCTNet: Uncertainty-Aware Cross-Modal Transformer Network for Indoor RGB-D Semantic Segmentation
* UFO: Unified Feature Optimization
* UIA-ViT: Unsupervised Inconsistency-Aware Method Based on Vision Transformer for Face Forgery Detection
* Ultra-High-Resolution Unpaired Stain Transformation via Kernelized Instance Normalization
* Unbiased Gradient Estimation for Differentiable Surface Splatting via Poisson Sampling
* Unbiased Manifold Augmentation for Coarse Class Subdivision
* Unbiased Multi-modality Guidance for Image Inpainting
* Uncertainty Inspired Underwater Image Enhancement
* Uncertainty Learning in Kernel Estimation for Multi-stage Blind Image Super-Resolution
* Uncertainty Quantification in Depth Estimation via Constrained Ordinal Regression
* Uncertainty-Aware Multi-modal Learning via Cross-Modal Random Network Prediction
* Uncertainty-Based Spatial-Temporal Attention for Online Action Detection
* Uncertainty-DTW for Time Series and Sequences
* Uncertainty-Guided Source-Free Domain Adaptation
* Understanding Collapse in Non-contrastive Siamese Representation Learning
* Understanding the Dynamics of DNNs Using Graph Modularity
* Unfolded Deep Kernel Estimation for Blind Image Super-Resolution
* UniCR: Universally Approximated Certified Robustness via Randomized Smoothing
* Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-Ahead Forward Ones
* UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation
* Unified Framework for Domain Adaptive Pose Estimation, A
* Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation
* Unified Implicit Neural Stylization
* Unifying Event Detection and Captioning as Sequence Generation via Pre-training
* Unifying Visual Contrastive Learning for Object Recognition from a Graph Perspective
* Unifying Visual Perception by Dispersible Points Learning
* UniMiSS: Universal Medical Self-supervised Learning via Breaking Dimensionality Barrier
* UniNet: Unified Architecture Search with Convolution, Transformer, and MLP
* Union-Set Multi-source Model Adaptation for Semantic Segmentation
* UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling
* Unitail: Detecting, Reading, and Matching in Retail Scene
* United Defocus Blur Detection and Deblurring via Adversarial Promoting Learning
* Unknown-Oriented Learning for Open Set Domain Adaptation
* Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
* Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning
* Unpaired Image Translation via Vector Symbolic Architectures
* UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture
* Unstructured Feature Decoupling for Vehicle Re-identification
* Unsupervised and Semi-supervised Bias Benchmarking in Face Recognition
* Unsupervised Deep Multi-Shape Matching
* Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-training
* Unsupervised Domain Adaptation for One-Stage Object Detector Using Offsets to Bounding Box
* Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space
* Unsupervised High-Fidelity Facial Texture Generation and Reconstruction
* Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction
* Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations
* Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression
* Unsupervised Pose-aware Part Decomposition for Man-Made Articulated Objects
* Unsupervised Segmentation in Real-World Images via Spelke Object Inference
* Unsupervised Selective Labeling for More Effective Semi-supervised Learning
* Unsupervised Visual Representation Learning by Synchronous Momentum Grouping
* V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer
* Variance-Aware Weight Initialization for Point Convolutional Neural Networks
* VecGAN: Image-to-Image Translation with Interpretable Latent Directions
* Vector Quantized Image-to-Image Translation
* Vibration-Based Uncertainty Estimation for Learning from Limited Supervision
* Video Activity Localisation with Uncertainties in Temporal Boundary
* Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles
* Video Dialog as Conversation About Objects Living in Space-Time
* Video Extrapolation in Space and Time
* Video Graph Transformer for Video Question Answering
* Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer
* Video Interpolation by Event-Driven Anisotropic Adjustment of Optical Flow
* Video Mask Transfiner for High-Quality Video Instance Segmentation
* Video Question Answering with Iterative Video-Text Co-tokenization
* Video Restoration Framework and Its Meta-adaptations to Data-Poor Conditions
* View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums
* ViewFormer: NeRF-Free Neural Rendering from Few Images Using Transformers
* ViP: Unified Certified Detection and Recovery for Patch Attack with Vision Transformers
* VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data
* VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection
* Visual Cross-View Metric Localization with Dense Uncertainty Estimates
* Visual Knowledge Tracing
* Visual Navigation Perspective for Category-Level Object Pose Estimation, A
* Visual Prompt Tuning
* ViTAS: Vision Transformer Architecture Search
* VizWiz-FewShot: Locating Objects in Images Taken by People with Visual Impairments
* VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
* Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting
* VoViT: Low Latency Graph-Based Audio-Visual Voice Separation Transformer
* VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
* VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance
* VSA: Learning Varied-Size Window Attention in Vision Transformers
* VTC: Improving Video-Text Retrieval with User Comments
* W2N: Switching from Weak Supervision to Noisy Supervision for Object Detection
* Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal
* Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning
* WaveGAN: Frequency-Aware GAN for High-Fidelity Few-Shot Image Generation
* Waymo Open Dataset: Panoramic Video Panoptic Segmentation
* Weakly Supervised 3D Scene Segmentation with Region-Level Boundary Awareness and Instance Discrimination
* Weakly Supervised Grounding for VQA in Vision-Language Transformers
* Weakly Supervised Object Localization Through Inter-class Feature Similarity and Intra-class Appearance Consistency
* Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration
* Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation
* Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions
* Webly Supervised Concept Expansion for General Purpose Vision Models
* Weight Fixing Networks
* WeLSA: Learning to Predict 6D Pose from Weakly Labeled Data Using Shape Alignment
* What Matters for 3D Scene Flow Network
* What to Hide from Your Students: Attention-Guided Masked Image Modeling
* When Active Learning Meets Implicit Semantic Data Augmentation
* When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition
* When Deep Classifiers Agree: Analyzing Correlations Between Learning Order and Image Statistics
* Where in the World Is This Image? Transformer-Based Geo-localization in the Wild
* Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification
* WISE: Whitebox Image Stylization by Example-Based Learning
* Word-Level Fine-Grained Story Visualization
* Worst Case Matters for Few-Shot Recognition
* X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks
* X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation
* XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
* You Already Have It: A Generator-Free Low-Precision DNN Training Framework Using Stochastic Rounding
* You Should Look at All Objects
* Zero-Shot Attribute Attacks on Fine-Grained Recognition Models
* Zero-Shot Category-Level Object Pose Estimation
* Zero-Shot Learning for Reflection Removal of Single 360-Degree Image
* Zero-Shot Temporal Action Detection via Vision-Language Prompting
1646 for ECCV22

ECCV90 * *ECCV
* 3-D Curve Matching Using Splines
* 3D interpretation system based on consistent labeling of a set of propositions. Application to the interpretation of straight line correspondences, A
* 3D-vision-based robot navigation: First steps
* Adapting computer vision systems to the visual environment: Topographic mapping
* Ambiguity in Reconstruction from Image Correspondences
* Analysis of Knowledge Representation Schemes for High Level Vision, An
* analysis of time varying image sequences, The
* Analytic Results on Error Sensitivity of Motion Estimation from Two Views
* B-Spline Contour Representations and Symmetry Detection
* Biased anisotropic diffusion: A unified regularization and diffusion approach to edge detection
* bit plane architecture for an image analysis processor implemented with P.L.C.A. gate array, A
* Charting surface structure
* Combinatorial characterization of perspective projections from polyhedral object scenes
* Combinatorics of Heuristic Search Termination for` Object Recognition in Cluttered Environments, The
* Comparison of Stochastic and Deterministic Solution Methods in Bayesian Estimation of 2-D Motion, A
* Deformable templates for feature extraction from medical images
* Derivation of Qualitative Information in Motion Analysis, The
* Detection and Tracking of Moving Objects Based on a Statistical Regularization Method in Space and Time
* Direct Evidence for Occlusion in Stereo and Motion
* Distributed learning of texture classification
* dynamic generalized Hough transform, The
* Dynamic World Modeling Using Vertical Line Stereo
* Edge Contours using Multiple Scales
* Estimation of 3D-Motion and Structure from Tracking 2D-Lines in a Sequence of Images
* Estimation of Curvature in 3D Images Using Tensor Field Filtering
* Experiments on the Use of the ATMS to Lagel Features for Object Recognition
* Extending the Oriented Smoothness Constraint into the Temporal Domain and the Estimation of Derivatives of Optical Flow
* Extraction of deformable part models
* Fast Shape from Shading
* Final steps towards real time trinocular stereovision
* Finding Geometric and Relational Structures in an Image
* heterogeneous vision architecture, A
* Hierarchical Image Analysis Using Irregular Tessellations
* incremental rigidity scheme for structure from motion: The line-based formulation, The
* Inverse perspective of a triangle: New exact and approximate solutions
* Local cross-modality image alignment using unsupervised learning
* Measurement and Integration of 3-D Structures by Tracking Edge Lines
* model for the estimate of local velocity, A
* Model-Based Object Recognition by Geometric Hashing
* Motion Determination in Space-Time Images
* Object detection and identification by hierarchical segmentation
* Object Detection Using Model Based Prediction and Motion Parallax
* Object Recognition Using Local Geometric Constraints: A Robust Alternative to Tree-Search
* Obstacle Detection by Evaluation of Optical Flow Fields from Image Sequences
* On Scale and Resolution in the Analysis of Local Image Structure
* On the Estimation of Depth from Motion Using an Anthropomorphic Visual Sensor
* On the Motion of 3D Curves and Its Relationship to Optical Flow
* On the use of motion concepts for top-down control in traffic scenes
* On the Use of Trajectory Information to Assist Stereopsis in a Dynamic Environment
* On the Verification of Hypothesized Matches in Model-Based Recognition
* Optimal filter for edge detection methods and results
* optimal solution for mobile camera calibration, An
* Parallel and Deterministic Algorithms from MRFs: Surface Reconstruction and Integration
* Parallel Computation of Optic Flow
* Parallel Multiscale Stereo Matching Using Adaptive Smoothing
* Projectively Invariant Representations Using Implicit Algebraic Curves
* Pyramidal Stereovision Algorithm Based on Contour Chain Points, A
* Recovery of Volumetric Object Descriptions from Laser Rangefinder Images
* Recursive Filtering and Edge Closing: Two Primary Tools for 3D Edge Detection
* Road following algorithm using a panned plan-view transformation
* Robust Estimation of Surface Curvature from Deformation of Apparent Contours
* Scale-Space Singularities
* Shading into texture and texture into shading: An active approach
* Shape and mutual cross-ratios with applications to exterior, interior and relative orientation
* Shape from Contour Using Symmetries
* SIMD geometric matching
* Snake growing
* Spatial Context in an Image Analysis System
* Spatial Localization of Modelled Objects of Revolution in Monocular Perspective Vision
* Stabilized Solution for 3-D Model Parameters
* Stereo correspondence from optic flow
* Stereo integration, mean field theory and psychophysics
* Stereo matching based on a combination of simple features used for matching in temporal image sequences
* Structure-from-Motion under Orthographic Projection
* Toward a Computational Theory of Shape: An Overview
* Tracking in a complex visual environment
* Tracking Line Segments
* Transparent-motion analysis
* Using neural networks to learn shape decomposition by successive prototypication
* Using occluding contours for 3D object modeling
* Vertical and Horizontal Disparities from Phase
82 for ECCV90

ECCV92 * *ECCV
* 3-D object recognition using passively sensed range data
* Active Detection and Classification of Junctions by Foveation with a Head-Eye System Guided by the Scale-Space Primal Sketch
* Active Egomotion Estimation: A Qualitative Approach
* Active perception using DAM and estimation techniques
* Active/Dynamic Stereo for Navigation
* Applying two-dimensional delaunay triangulation to stereo data interpolation
* Attentional Prototype for Early Vision, An
* Bayesian Multiple-Hypothesis Approach to Contour Grouping, A
* Boundary detection in piecewise homogeneous textured images
* Camera Calibration Using Multiple Images
* Camera Self-Calibration: Theory and Experiments
* Canonical Frames for Planar Object Recognition
* Combining intensity and motion for incremental segmentation and tracking over long image sequences
* Computational Framework for Determining Stereo Correspondence from a Set of Linear Spatial Filters
* Computing Exact Aspect Graphs of Curved Objects: Algebraic Surfaces
* Constraints for Recognizing and Locating Curved 3D Objects from Monocular Image Features
* Contour extraction by mixture density description obtained from region clustering
* Critical sets for 3D reconstruction using lines
* Data and Model-Driven Selection Using Color Regions
* Depth Computations from Polyhedral Images
* Detecting 3D Parallel Lines for Perceptual Organization
* Detecting and Tracking Multiple Moving Objects Using Temporal Integration
* Detection of general edges and keypoints
* Detection of Specularity Using Colour and Multiple Views
* Determining Three-Dimensional Shape from Orientation and Spatial Frequency Disparities
* Deterministic Approach for Stereo Disparity Calculation, A
* Deterministic pseudo-annealing: Optimization in Markov-Random-Fields an application to pixel classification
* Distributed belief revision for adaptive image processing regulation
* Edge Classification and Depth Reconstruction by Fusion of Range and Intensity Edge Data
* Edge Tracing in a Priori Known Direction
* Egomotion Algorithm Based on the Tracking of Arbitrary Curves, An
* Ellipse based stereo vision
* Epipolar Line Estimation
* Estimation of Relative Camera Positions for Uncalibrated Cameras
* Extraction of Line Drawings from Gray Value Images by Non-Local Analysis of Edge Element Structures
* Face Recognition Through Geometrical Features
* Families of Tuned Scale-Space Kernels
* Fast Method to Estimate Sensor Translation, A
* Fast Obstacle Detection Method Based on Optical Flow, A
* Features extraction and analysis methods for sequences of ultrasound Images
* Figure-Ground Discrimination by Mean Field Annealing
* Finding clusters and planes from 3D line segments with application to 3D motion determination
* Finding Face Features
* Finding Parametric Curves in an Image
* Finding the Pose of an Object of Revolution
* Fusion Through Interpretation
* Gaze Control for a Binocular Camera Head
* Hardware support for fast edge-based stereo
* Hierarchical Model-Based Motion Estimation
* Hierarchical shape recognition based on 3-D multiresolution analysis
* Identifying Multiple Motions from Optical Flow
* Image Blurring Effects Due to Depth Discontinuities: Blurring That Creates Emergent Image Details
* Image compression and reconstruction using a 1-D feature catalogue
* Indexicality and dynamic attention control in qualitative recognition of assembly actions
* Integrated skeleton and boundary shape representation for medical image interpretation
* Integrating Primary Ocular Processes
* Intensity and Edge-Based Symmetry Detection Applied to Car Following
* Interpretation of Remotely Sensed Images in a Context of Multisensor Fusion
* Intrinsic surface properties from surface triangulation
* Learning to Recognize Faces from Examples
* Limitations of Non Model-Based Recognition Schemes
* Local Stereoscopic Depth Estimation Using Ocular Stripe Maps
* Matching and Recognition of Road Networks from Aerial Images
* Measuring the Quality of Hypotheses in Model-Based Recognition
* method for the 3D reconstruction of indoor scenes from monocular images, A
* Model-Based Object Pose in 25 Lines of Code
* Model-Based Object Tracking in Traffic Scenes
* Motion and Structure Factorization and Segmentation of Long Multiple Motion Image Sequences
* Motion and Surface Recovery Using Curvature and Motion Consistency
* Möbius strip parameterization for line extraction, The
* new topological classification of points in 3D images, A
* Object Recognition by Flexible Template Matching Using Genetic Algorithms
* Occlusions and Binocular Stereo
* On visual ambiguities due to transparency in motion and stereo
* Parallel algorithms for the distance transformation
* parallel implementation of a structure-from-motion algorithm, A
* Polynomial-Time Object Recognition in the Presence of Clutter, Occlusions, and Uncertainty
* Real-Time Visual Tracking for Surveillance and Path Planning
* Recognizing Rotationally Symmetric Surfaces from Their Outlines
* Recovering Shading from Color Images
* Region-Based Tracking in an Image Sequence
* Robust and fast computation of unbiased intensity derivatives in images
* Segmenting Unstructured 3D Points into Surfaces
* Shading Flows and Scenel Bundles: A New Approach to Shape from Shading
* Shape from Texture for Smooth Curved Surfaces
* Shape from Texture for Smooth Curved Surfaces in Perspective Projection
* Smoothing and Matching of 3-D Space Curves
* Spatio-Temporal Reasoning within a Traffic Surveillance System
* Steerable-Scalable Kernels for Edge Detection and Junction Analysis
* Structure from Motion Using Ground Plane Constraint
* Study of Affine Matching with Bounded Sensor Error, A
* Surface Interpolation Using Wavelets
* Surface Orientation and Time to Contact from Image Divergence and Deformation
* Template Guided Visual Inspection
* Testing computational theories of motion discontinuities: A psychophysical study
* Texture Parametrization Method For Image Segmentation
* Texture Segmentation by Minimizing Vector-Valued Energy Functionals: The Coupled-Membrane Model
* Texture: Plus Ca Change
* theory of 3D reconstruction of heterogeneous edge primitives from two perspective views, A
* Tracking Moving Contours Using Energy-Minimizing Elastic Contour Models
* Tracking Points on Deformable Objects Using Curvature Information
* Using Automatically Constructed View-Independent Relational Model in 3D Object Recognition
* Using Deformable Surfaces to Segment 3-D Images and Infer Differential Structures
* Using Force Fields Derived from 3D Distance Maps for Inferring the Attitude of a 3D Rigid Object
* What Can Be Seen in Three Dimensions with an Uncalibrated Stereo Rig?
* Where to Look Next Using a Bayes Net: An Overview
107 for ECCV92

ECCV94 * *ECCV
* 3-D Stereo Using Photometric Ratios
* Active 3D Object Recognition Using 3D Affine Invariants
* Active Camera Self-Orientation Using Dynamic Image Parameters
* Active Object Recognition Integrating Attention and Viewpoint Control
* Affine and Projective Normalization of Planar Curves and Regions
* Analytical Methods for Uncalibrated Stereo and Motion Reconstruction
* Applying VC-Dimension Analysis to Object Recognition
* Area and Length Preserving Geometric Invariant Scale-Spaces
* Association of Motion Verbs with Vehicle Movements Extracted from Dense Optical Flow Fields
* Camera Calibration from Spheres Images
* Camera Calibration of a Head-Eye System for Active Vision
* Camera Calibration of the KTH Head-Eye System
* Canonic Representations for the Geometries of Multiple Projective Views
* Common Framework for Kinetic Depth, Reconstruction and Motion for Deformable Objects, A
* Comparison between the Standard Hough Transform and the Mahalanobis Distance Hough Transform, A
* Comparisons of Probabilistic and Non-Probabilistic Hough Transforms
* Consistency and Correction of Line-Drawings, Obtained by Projections of Piecewise Planar Objects
* Deriving Orientation Cues from Stereo Images
* Determination of Optical Flow and Its Discontinuities Using Non-Linear Diffusion
* Direct Estimation of Local Surface Shape in a Fixating Binocular Vision System
* Direct Recovery of Superquadric Models in Range Images Using Recover-and-Select Paradigm, A
* Disparity-Space Images and Large Occlusion Stereo
* Divided we fall: Resolving occlusions using causal reasoning
* Epipolar Fields on Surfaces
* Evolutionary Fronts for Topology-Independent Shape Modeling and Recovery
* Extracting the Affine Transformation from Texture Moments
* Extraction of Groups for Recognition
* Face Recognition: The Problem of Compensating for Changes in Illumination Direction
* First Order Optic Flow from Log-Polar Sampled Images
* Following Corners on Curves and Surfaces in the Scale Space
* Framework For Low Level Feature Extraction, A
* Generating Spatiotemporal Models From Examples
* Genetic algorithms applied to binocular stereovision
* Geometry-Driven Curve Evolution
* Grasping the Apparent Contour
* Hierarchical Shape Representation Using Locally Adaptive Finite Elements
* Image Motion Estimation Technique Based on a Combined Statistical Test and Spatiotemporal Generalised Likelihood Ratio Approach, An
* Improving registration of 3-D medical images using a mechanical based method
* Independent Motion Segmentation and Collision Prediction for Road Vehicles
* Integrated 3D Analysis of Flight Image Sequences
* Integration and Control of Reactive Visual Processes
* Intrinsic Stabilizers of Planar Curves
* Invariants of 6 Points from 3 Uncalibrated Images
* Junction Classification by Multiple Orientation Detection
* Lack-of-fit detection using the run-distribution test
* Linear Pushbroom Cameras
* Markov Random Field Models in Computer Vision
* Measuring the Affine Transform Using Gaussian Filters
* Model Based Pose Estimation of Articulated and Constrained Objects
* Motion Boundary Detection in Image Sequences by Local Stochastic Tests
* Motion Estimation on the Essential Manifold
* Motion Field of Curves: Applications
* Motion from Point Matches Using Affine Epipolar Geometry
* MRF based motion detection algorithm implemented on analog resistive network, An
* Multiple Constraints for Optical Flow
* Navigation Using Affine Structure from Motion
* Non-Iterative Contextual Correspondence Matching
* Non-parametric local transforms for computing visual correspondence
* Occlusion Ambiguities in Motion
* On Perceptual Advantages Of Eye-Head Active Control
* On the Enumerative Geometry of Aspect Graphs
* Optical Flow Estimation: Advances and Comparisons
* Parameter-Free Information-Preserving Surface Restoration
* Paraperspective Factorization for Shape and Motion Recovery, A
* Performance Comparison of Ten Variations on the Interpretation-Tree Matching Algorithm
* Planning the Optimal Set of Views Using the Max-Min Principle
* Pose Determination and Recognition of Vehicles in Traffic Scenes
* Pose Refinement of Active Models Using Forces in 3D
* Projective Invariants for Planar Contour Recognition
* Pulsed neural networks and perceptive grouping
* Quadric Reference Surface: Applications in Registering Views of Complex 3D Objects, The
* Quantitative measurement of manufactured diamond shape
* Recognition of Human Facial Expressions without Feature Extraction
* Recognizing Hand Gestures
* Recovering Surface Curvature and Orientation from Texture Distortion: A Least Squares Algorithm and Sensitivity Analysis
* Recovery of Illuminant and Surface Colors from Images Based on the CIE Daylight
* Recursive Affine Structure and Motion from Image Sequences
* Recursive Non-Linear Estimation of Discontinuous Flow Fields
* Registration Method for Rigid Objects Without Point Matching, A
* Registration of a Curve on a Surface Using Differential Properties
* Relative 3D Regularized B-Spline Surface Reconstruction Through Image Sequences
* Rigid and Affine Registration of Smooth Surfaces Using Differential Properties
* Robust Egomotion Estimation from Affine Motion Parallax
* Robust Method for Road Sign Detection and Recognition, A
* Robust Multiple Car Tracking with Occlusion Reasoning
* Robust Recovery of the Epipolar Geometry for an Uncalibrated Stereo Rig
* Robust Tracking of 3D Motion, A
* Role of Key-Points in Finding Contours, The
* Scalar Function Formulation For Optical Flow, A
* Scale-Space Properties of Quadratic Edge Detectors
* Seeing Behind Occlusions
* Seeing Beyond Lambert's Law
* Segmentation and Recovery of SHGCS from a Real Intensity Image
* Segmentation of echocardiographic images with Markov random fields
* Segmentation of Moving Objects by Robust Motion Parameter Estimation over Multiple Frames
* Self Calibration of a Stereo Head Mounted onto a Robot Arm
* Self-Calibration from Multiple Views with a Rotating Camera
* Shape from Motion Algorithms: A Comparative Analysis of Scaled Orthography and Perspective
* Shape from Shading: Provably Convergent Algorithms and Uniqueness Results
* Shape Models from Image Sequences
* Shape-Adapted Smoothing in Estimation of 3-D Depth Cues from Affine Distortions of Local 2-D Structure
* Spatially Varying Illumination: A Computational Model of Converging and Diverging Sources
* Stability Analysis of the Fundamental Matrix, A
* Stability and Likelihood of Views of Three Dimensional Objects
* Stochastic Motion Clustering
* Sufficient Image Structure for 3-D Motion and Shape Estimation
* Synchronous image restoration
* Topological Reconstruction of a Smooth Manifold-Solid from its Occluding Contour
* Trilinearity in Visual Recognition by Alignment
* Unsupervised Regions Segmentation: Real Time Control of an Upkeep Machine of Natural Spaces
* Use of Optical Flow for the Autonomous Navigation, The
* Using 3-Dimensional Meshes to Combine Image-Based and Geometry-Based Constraints
* Utilizing Symmetry in the Reconstruction of Three-Dimensional Shape from Noisy Images
* Vibration Modes for Nonrigid Motion Analysis in 3D Images
* Visual Tracking of High DoF Articulated Structures: An Application to Human Hand Tracking
* What Can Two Images Tell Us about a Third One?
117 for ECCV94

ECCV96 * *ECCV
* 3D Model Acquisition from Extended Image Sequences
* Accuracy vs. Efficiency Trade-Offs in Optical Flow Algorithms
* Acquiring Visual-Motor Models for Precision Manipulation with Robot Hands
* Affine/Photometric Invariants for Planar Intensity Patterns
* Algebraic Varieties in Multiple View Geometry
* Application of Model Based Image Interpretation Methods of Diabetic Neuropathy
* Automatic Extraction of Generic House Roofs from High Resolution Aerial Imagery
* Automatic Face Recognition: What Representation?
* Automatic Selection of Reference Views for Image-Based Scene Representations
* Automatic Singularity Test for Motion Analysis by an Information Criterion
* Bidirectional Reflection Distribution Function Expressed in Terms of Surface Scattering Modes
* Class Based Reconstruction Techniques using Singular Apparent Contours
* Color Angular Indexing
* Color Constancy for Scenes with Varying Illumination
* Combining Multiple Motion Estimates for Vehicle Tracking
* Complexity of Indexing: Efficient and Learnable Large Database Indexing
* Computational Perception of Scene Dynamics, The
* Computing Contour Closure
* Computing Structure and Motion of General 3D Curves from Monocular Sequences of Perspective Images
* Contour Tracking by Stochastic Propagation of Conditional Density
* Decomposition of the Hough Transform: Curve Detection with Effcient Error Propagation
* Decoupling the 3D Motion Space by Fixation
* Dense Depth Map Reconstruction: A Minimization and Regularization Approach which Preserves Discontinuities
* Dense Reconstruction by Zooming
* Detecting, Localizing and Grouping Repeated Scene Elements from an Image
* Direct Differential Range Estimation Using Optical Masks
* Direct Methods for Self-Calibration of a Moving Stereo Head
* Directions of Motion Fields Are Hardly Ever Ambiguous
* Duality of Multi-Point and Multi-Frame Geometry: Fundamental Shape Matrices and Tensors
* Eigenfaces vs. Fisherfaces: Recognition Using Class-Specific Linear Projection
* EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
* Elastically Adaptive Deformable Models
* Elimination of Specular Surface-Reflectance Using Polarized and Unpolarized Light
* Euclidean 3D Reconstruction from Image Sequences with Variable Focal Lengths
* Euclidean Reconstruction: From Paraperspective to Perspective
* Extracting Curvilinear Structures: A Differential Geometric Approach
* Factorization Based Algorithm for Multi-Image Projective Structure and Motion, A
* Fast Computation of the Fundamental Matrix for an Active Stereo Vision System
* Filter for Visual Tracking Based on a Stochastic Model for Driver Behaviour, A
* Finding Naked People
* Flows under Min/Max Curvature Flow and Mean Curvature: Applications in Image Processing
* Focused Target Segmentation Paradigm, A
* Generalised Epipolar Constraints
* Generalized Image Matching: Statistical Learning of Physically-Based Deformations
* Generalizing Lambert's Law for Smooth Surfaces
* Generation of Semantic Regions from Image Sequences
* Genetic Search for Structural Matching
* Geometric Saliency of Curve Correspondences and Grouping of Symmetric Contours
* Global Alignment of MR Images Using a Scale Based Hierarchical Model
* Goal-Directed Video Metrology
* Ground Plane Motion Camera Models
* Hierarchical Curve Reconstruction. Part I: Bifurcation Analysis and Recovery of Smooth Curves
* Human Body Tracking by Monocular Vision
* Image Recognition with Occlusions
* Image Retrieval Using Scale-Space Matching
* Image Synthesis from a Single Example Image
* Imposing Hard Constraints on Soft Snakes
* Informative Views and Sequential Recognition
* Learning Dynamics of Complex Motions from Image Sequences
* Local Appropriate Scale in Morphological Scale-Space
* Local Quantitative Measurements for Cardiac Motion Analysis
* Local Scale Control for Edge Detection and Blur Estimation
* Locating Objects of Varying Shape Using Statistical Feature Detectors
* Matching Object Models to Segments from an Optical Flow Field
* Maximum-Likelihood Approach to Visual Event Classification, A
* Measures for Silhouettes Resemblance and Representative Silhouettes of Curved Objects
* Motion Deblurring and Super-Resolution from an Image Sequence
* Nonlinear scale-space from n-dimensional sieves
* Normalization by Optimization
* Object models from contour sequences
* Object Recognition Using Multidimensional Receptive Field Histograms
* Object Recognition Using Subspace Methods
* On Binocularly Viewed Occlusion Junctions
* On the Appropriateness of Camera Models
* Optical Flow and Phase Portrait Methods for Environmental Satellite Image Sequences
* Optimal Surface Smoothing as Filter Design
* Oriented Projective Geometry for Computer Vision
* Parallax Geometry of Pairs of Points for 3D Scene Analysis
* Quantification of Articular Cartilage from MR Images Using Active Shape Models
* Quantitative Analysis of Grouping Processes
* Rank 4 Constraint in Multiple (over 3) View Geometry, The
* Rapid Object Indexing and Recognition Using Enhanced Geometric Hashing
* Real-Time Lip Tracking for Audio-Visual Speech Recognition Applications
* Reasoning about Occlusions During Hypothesis Verification
* Recognition of Geons by Parametric Deformable Contour Models
* Recognition, Pose and Tracking of Modelled Polyhedral Objects by Multi-Ocular Vision
* Reconstructing Polyhedral Models of Architectural Scenes from Photographs
* Reconstruction of Blood Vessel Networks From X-Ray Projections and a Vascular Catalogue
* Refinement of Optical Flow Estimation and Detection of Motion Edges
* Regularization, Scale-Space, and Edge-Detection Filters
* Reliable Extraction of the Camera Motion Using Constraints on the Epipole
* Reliable Surface Reconstruction from Multiple Range Images
* Rigorous Bounds for Two-Frame Structure from Motion
* Robust Active Contour Model for Natural Scene Contour Extraction with Automatic Thresholding, A
* Robust Affine Structure Matching for 3d Object Recognition
* Scale-Space with Causal Time Direction
* Segmentation in Dynamic Image Sequences by Isolation of Coherent Wave Profiles
* Self-Calibration from Image Triplets
* Separating Real and Virtual Objects from Their Overlapping Images
* Shape Ambiguities In Structure-From-Motion
* Shape from Appearance: A Statistical Approach to Surface Shape Estimation
* Silhouette-Based Occluded Object Recognition Through Curvature Scale-Space
* Snakes and Splines for Tracking Non-Rigid Heart Motion
* Spatiotemporal Representations for Visual Navigation
* Statistical Feature Modelling for Active Contours
* Stereo without Search
* System for Reconstruction of Missing Data in Image Sequences Using Sampled 3D AR Models and MRF Motion Priors, A
* Telecentric Optics for Computational Vision
* Texture Feature Coding Method for Classification of Liver Sonography
* Texture Segmentation Using Local Energy in Wavelet Scale Space
* Three Dimensional Object Modeling via Minimal Surfaces
* Tracing Crease Curves by Solving a System of Differential Equations
* Tracking Medical 3D Data with a Deformable Parametric Model
* Tracking Occluded Vehicles in Traffic Scenes
* Uncalibrated Relief Reconstruction and Model Alignment from Binocular Disparities
* Uncalibrated Visual Tasks via Linear Interaction
* Understanding the Shape Properties of Trihedral Polyhedra
* Unsupervised Texture Segmentation Using Selectionist Relaxation
* Using Singular Displacements for Uncalibrated Monocular Visual Systems
* Visual Organization of Illusory Surfaces
* Visual Surveillance Monitoring and Watching
* Volumetric Segmentation Using Hierarchical Representation And Triangulated Surface
* X Vision: Combining Image Warping and Geometric Constraints for Fast Visual Tracking
124 for ECCV96

ECCV98 * *ECCV
* 2-D-Object Tracking Based on Projection-Histograms
* Active Appearance Models
* Autocalibration from planar scenes
* Automatic camera recovery for closed or open image sequences
* Automatic Detection and Labelling of the Human Cortical Folds in Magnetic Resonance Data Sets
* Automatic Modelling and 3-D Reconstruction of Urban House Roofs from High Resolution Aerial Imagery
* Beginning a Transition from a Local to a More Global Point of View in Model-Based Vehicle Tracking
* Bias-Variance Tradeoff for Adaptive Surface Meshes
* Camera-Based ID Verification by Signature Tracking
* Changes in Surface Convexity and Topology Caused by Distortions of Stereoscopic Visual Space
* Closed-form solutions for the Euclidean calibration of a stereo rig
* Colour model selection and adaptation in dynamic scenes
* Combining Geometric and Probabilistic Structure for Active Recognition of 3-D Objects
* Combining Multiple Views and Temporal Associations for 3-D Object Recognition
* common framework for multiple view tensors, A
* Comparison of Active Shape Model and Scale Decomposition Based Features for Visual Speech Recognition, A
* Comparison of Measures for Detecting Natural Shapes in Cluttered Backgrounds, A
* Complete dense stereovision using level set methods
* Comprehensive colour image normalization
* Computation of the quadrifocal tensor
* Concerning Bayesian Motion Segmentation, Model Averaging, Matching and the Trifocal Tensor
* Continuous Audio-Visual Speech Recognition
* Contour continuity in region-based image segmentation
* Creaseness from Level Set Extrinsic Curvature
* Decoupling Fourier Components of Dynamic Image Sequences: A Theory of Signal Separation, Image Segmentation, and Optical Flow Estimation
* Demosaicing: Image Reconstruction from Color CCD Samples
* Determining a Structured Spatio-Temporal Representation of Video Content for Efficient Visualization and Indexing
* Discrete Wavelet Analysis: A New Framework for Fast Optic Flow Computation
* Do we really need an accurate calibration pattern to achieve a reliable camera calibration?
* Duality, Rigidity and Planar Parallax
* Efficient 3-D Scene Visualization by Image Extrapolation
* Efficient Combination of 2-D and 3-D Shape Descriptions for Contour-Based Tracking of Moving Objects, An
* Epipolar Geometry for Panoramic Cameras
* Estimating Coloured 3-D Face Models from Single Images: An Example-Based Approach
* Face recognition using active appearance models
* Face recognition using evolutionary pursuit
* Factorization Approach to Grouping, A
* Factorization Method for Projective and Euclidean Reconstruction from Multiple Perspective Views via Iterative Depth Estimation, A
* Faithful Least-Squares Fitting of Spheres, Cylinders, Cones and Tori for Reliable Segmentation
* Finding Boundaries in Natural Images: A New Method Using Point Descriptors and Area Completion
* Finding Surface Correspondence for Object Recognition and Registration Using Pairwise Geometric Histograms
* Flexible syntactic matching of curves
* From Reference Frames to Reference Planes: Multi-View Parallax Geometry and Applications
* From regular images to animated heads: A least squares approach
* geometry and matching of curves in multiple views, The
* Handling uncertainty in 3-D object recognition using Bayesian networks
* Holistic matching
* Hypothesis Verification in Model-Based Object Recognition with a Gaussian Error Model
* ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework
* Image Sequence Restoration: A PDE-Based Coupled Method for Image Restoration and Motion Segmentation
* Integrating Iconic and Structured Matching
* Invariant-Based Shape Retrieval in Pictorial Databases
* Is machine colour constancy good enough?
* Joint Estimation-Segmentation of Optic Flow
* Matching Hierarchical Structures Using Association Graphs
* Mis?-) Using DRT for Generation of Natural Language Text from Image Sequences
* Mobile robot localisation using active vision
* Model based tracking for navigation and segmentation
* Model-Based Recognition of 3-D Objects from One View
* Model-Free Voting Approach for Integrating Multiple Cues, A
* Modelling Objects Having Quadric Surfaces Incorporating Geometric Constraints
* Motion Recovery from Image Sequences: Discrete Viewpoint vs. Differential Viewpoint
* Motion Segmentation and Depth Ordering Based on Morphological Segmentation
* Multi viewpoint stereo from uncalibrated video sequences
* Multi-Scale and Snakes for Automatic Road Extraction
* Multi-Step Procedures for the Localization of 2-D and 3-D Point Landmarks and Automatic ROI Size Selection
* Multichannel shape from shading techniques for moving specular surfaces
* new characterization of the trifocal tensor, A
* Object-oriented motion estimation in color image sequences
* Occlusions, discontinuities, and epipolar lines in stereo
* On Degeneracy of Linear Reconstruction From Three Views: Linear Line Complex and Applications
* On Spatial Quantization of Color Images
* Optical Flow Using Overlapped Basis Functions for Solving Global Motion Problems
* Optimal estimation of three-dimensional rotation and reliability evaluation
* Optimal robot self-localization and reliability evaluation
* Perceptual Smoothing and Segmentation of Colour Textures
* Probabilistic Approach to Object Recognition Using Local Photometry and Global Geometry, A
* Probabilistic Framework for Matching Temporal Trajectories: CONDENSATION-Based Recognition of Gestures and Expressions, A
* Projective and Illumination Invariant Representation of Disjoint Shapes
* Recognition of planar point configurations using the density of affine shape
* Recognizing 3-D objects with linear support vector machines
* Recognizing faces by weakly orthogonalizing against perturbations
* Reconstruction of Smooth Surfaces with Arbitrary Topology Adaptive Splines
* Robust Registration of Dissimilar Single and Multi-Modal Images
* Robust Techniques for the Estimation of Structure from Motion in the Uncalibrated Case
* Robust Video Mosaicing Through Topology Inference and Local to Global Alignment
* role of total least squares in motion analysis, The
* Self-Calibration of a 1D Projective Camera and Its Application to the Self-Calibration of a 2D Projective Camera
* Self-Inducing Relational Distance and its Application to Image Segmentation
* Shape from Chebyshev nets
* Shape representations from shading primitives
* Simultaneous estimation of viewing geometry and structure
* Smoothing Filter for CONDENSATION, A
* Solution for the Registration of Multiple 3-D Point Sets Using Unit Quaternions, A
* Spatial dependence in the observation of visual contours
* Spatiotemporally Adaptive Estimation and Segmentation of Optical Flow Fields
* Stereo Matching with Implicit Detection of Occlusions
* Stereo vision-based navigation in unknown indoor environment
* Structure and motion from points, lines and conics with affine cameras
* structure of the optic flow field, The
* Study of Dynamical Processes with Tensor-Based Spatiotemporal Image Processing Techniques
* Surface Reconstruction with Multiresolution Discontinuity Analysis
* Symmetry in perspective
* Threading Fundamental Matrices
* Three Steps to Make Shape from Shading Work Consistently on Real Scenes
* two-stage probabilistic approach for object recognition, A
* Use Your Hand as a 3-D Mouse or Relative Orientation from Extended Sequences of Sparse Point and Line Correspondences Using the Affine Trifocal Tensor
* Using IFs and Moments to Build a Quasi Invariant Image Index
* View-Based Adaptive Affine Tracking
* Visual Recognition Using Local Appearance
* W4S: A real-time system for detecting and tracking people in 2 1/2-D
* What Is Computed by Structure from Motion Algorithms?
* What shadows reveal about object structure
114 for ECCV98

ECCVDemos12 * *ECCV
* 3D Gesture Touchless Control Based on Real-Time Stereo Matching
* Adasens Advanced Driver Assistance Systems Live Demo
* Emotion Mirror: A Novel Intervention for Autism Based on Real-Time Expression Recognition
* Face-Based Illuminant Estimation
* FaceHugger: The ALIEN Tracker Applied to Faces
* Fast and Precise Template Matching Based on Oriented Gradients
* Human vs. Machine Challenge in Fashion Color Classification, A
* Instant Scene Recognition on Mobile Platform
* INTAIRACT: Joint Hand Gesture and Fingertip Classification for Touchless Interaction
* Leiden Augmented Reality System (LARS), The
* LZM in Action: Realtime Face Recognition System
* Object Categorization Based on a Supervised Mean Shift Algorithm
* Object-Layout-Aware Image Retrieval for Personal Album Management
* Prosemantic Image Retrieval
* Real-Time 3D Motion Capture by Monocular Vision and Virtual Rendering
* Real-Time Image Registration of RGB Webcams and Colorless 3D Time-of-Flight Cameras
* Real-Time Scene Text to Speech System, A
* Tai Chi Training System Based on Fast Skeleton Matching Algorithm, A
* Technical Demonstration on Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes
* Understanding Road Scenes Using Visual Cues and GPS Information
* Unsupervised Activity Analysis and Monitoring Algorithms for Effective Surveillance Systems
* Using 3D Models for Real-Time Facial Feature Tracking, Pose Estimation, and Expression Monitoring
23 for ECCVDemos12

ECCVWS18 * Workshop on Interactive and Adaptive Learning in an Open World

Index for "e"


Last update:16-Mar-24 21:12:13
Use price@usc.edu for comments.