Soatti, G.
* 2018: Implicit Cooperative Positioning in Vehicular Networks
* 2020: Augmenting Vehicle Localization by Cooperative Sensing of the Driving Environment: Insight on Data Association in Urban Traffic Scenarios
Soatto, S.
* 1993: Recursive Motion and Structure Estimation with Complete Error Characterization
* 1994: Dynamic visual motion estimation from subspace constraints
* 1994: Motion Estimation on the Essential Manifold
* 1994: Recursive estimation of camera motion from uncalibrated image sequences
* 1995: Dynamic Rigid Motion Estimation from Weak Perspective
* 1995: Visual motion estimation from point features: unified view
* 1996: geometric framework for dynamic vision, A
* 1996: Motion estimation via dynamic vision
* 1996: Motion from Fixation
* 1996: Reducing Structure from Motion: A General Framework for Dynamic Vision with Experimental Evaluation
* 1997: Motion from Fixation
* 1997: Recursive 3-D Visual-Motion Estimation Using Subspace Constraints
* 1998: Optimal Structure from Motion: Local Ambiguities and Global Estimates
* 1998: Reducing Structure-From-Motion: A General Framework For Dynamic Vision Part 1: Modeling
* 1998: Reducing Structure-From-Motion: A General Framework for Dynamic Vision Part 2: Implementation And Experimental Assessment
* 1998: Reducing Structure-From-Motion: A General Framework for Dynamic Vision Part 2: Implementation And Experimental Assessment
* 1999: Euclidean Reconstruction and Reprojection Up to Subgroups
* 1999: On observing shape from defocused images
* 2000: 3-D Motion and Structure from 2-D Motion Causally Integrated over Time: Implementation
* 2000: Euclidean Reconstruction and Reprojection Up to Subgroups
* 2000: Geometric Approach to Blind Deconvolution with Application to Shape from Defocus, A
* 2000: Optimal Structure from Motion: Local Ambiguities and Global Estimates
* 2000: Real-time 3D motion and structure of point features: a front-end system for vision-based control and interaction
* 2000: Shape and Radiance Estimation from the Information Divergence of Blurred Images
* 2000: Stereoscopic Shading: Integrating Multi-Frame Shape Cues in a Variational Framework
* 2001: Dynamic Texture Recognition
* 2001: Dynamic Textures
* 2001: Real-Time Feature Tracking and Outlier Rejection with Changes in Illumination
* 2001: Real-time Virtual Object Insertion
* 2001: Recognition of Human Gaits
* 2001: semi-direct approach to structure from motion, A
* 2001: Stereoscopic Segmentation
* 2002: DEFORMOTION: Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images
* 2002: Editable dynamic textures
* 2002: Editable dynamic textures
* 2002: Inpainting from multiple views
* 2002: Landmark based inpainting from multiple views
* 2002: Learning Shape from Defocus
* 2002: model (In)validation approach to gait recognition, A
* 2002: Region Matching with Missing Parts
* 2002: Structure from Motion Causally Integrated Over Time
* 2002: Variational multiframe stereo in the presence of specular reflections
* 2003: 3D shape from anistropic diffusion
* 2003: Deformotion: Deforming Motion, Shape Average and the Joint Registration and Approximation of Structures in Images
* 2003: Dynamic texture segmentation
* 2003: Dynamic Textures
* 2003: Editable dynamic textures
* 2003: Estimation of 3D surface shape and smooth radiance from 2D images: A Level Set Approach
* 2003: Multi-view stereo beyond Lambert
* 2003: Observing Shape from Defocused Images
* 2003: On exploiting occlusions in multiple-view geometry
* 2003: Seeing beyond occlusions (and other marvels of a finite lens aperture)
* 2003: semi-direct approach to structure from motion, A
* 2003: Shape representation via harmonic embedding
* 2003: Stereoscopic Segmentation
* 2003: Structure from motion for scenes without features
* 2003: Tales of shape and radiance in multi-view stereo
* 2003: Variational space-time motion segmentation
* 2004: Kernel Density Estimation and Intrinsic Alignment for Knowledge-Driven Segmentation: Teaching Level Sets to Walk
* 2004: Modeling and Synthesis of Facial Motion Driven by Speech
* 2004: Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis
* 2004: Region-Based Segmentation on Evolving Surfaces with Application to 3D Reconstruction of Shape and Piecewise Constant Radiance
* 2004: Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion
* 2004: Shedding light on stereoscopic segmentation
* 2004: Spatially Homogeneous Dynamic Textures
* 2004: Variational Approach to Problems in Calibration of Multiple Cameras, A
* 2004: variational approach to scene reconstruction and image segmentation from motion-blur cues, A
* 2005: Dynamic Shape and Appearance Modeling via Moving and Deforming Layers
* 2005: Features for Recognition: Viewpoint Invariance for Non-Planar Scenes
* 2005: Geometric Approach to Shape from Defocus, A
* 2005: Invitation to 3-D Vision: From Images to Geometric Models, An
* 2005: KALMANSAC: Robust Filtering by Consensus
* 2005: Layered Active Appearance Models
* 2005: Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation
* 2005: Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance
* 2005: One-Shot Integral Invariant Shape Priors for Variational Segmentation
* 2006: Classifying Human Dynamics Without Contact Forces
* 2006: Control Theory and Fast Marching Methods for Brain Connectivity Mapping
* 2006: Control Theory and Fast Marching Techniques for Brain Connectivity Mapping
* 2006: Dynamic Shape and Appearance Models
* 2006: Harmonic Embeddings for Linear Shape Analysis
* 2006: Integral Invariants for Shape Matching
* 2006: Kernel Density Estimation and Intrinsic Alignment for Shape Priors in Level Set Segmentation
* 2006: Local Features, All Grown Up
* 2006: Region Matching with Missing Parts
* 2006: Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation
* 2006: Towards Robust and Physically Plausible Shaded Stereoscopic Segmentation
* 2006: Two-View Multibody Structure from Motion
* 2006: Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions
* 2007: 3-D Shape Estimation and Image Restoration: Exploiting Defocus and Motion-Blur
* 2007: Autocalibration and Uncalibrated Reconstruction of Shape from Defocus
* 2007: Classification and Recognition of Dynamical Models: The Role of Phase, Independent Components, Kernels and Optimal Transport
* 2007: Correspondence Transfer for the Registration of Multimodal Images
* 2007: Exploring Tradeoffs in Accuracy, Energy and Latency of Scale Invariant Feature Transform in Wireless Camera Networks
* 2007: Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression
* 2007: Joint Priors for Variational Shape and Appearance Modeling
* 2007: Moving Forward in Structure From Motion
* 2007: Mumford-Shah on the Move: Region-Based Segmentation on Deforming Manifolds with Application to 3-D Reconstruction of Shape and Appearance from Multi-View Images
* 2007: On the Blind Classification of Time Series
* 2007: Proximity Distribution Kernels for Geometric Context in Category Recognition
* 2007: Study of Face Recognition as People Age, A
* 2007: Variational Approach to Problems in Calibration of Multiple Cameras, A
* 2008: 3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illumination
* 2008: Background Subtraction on Distributions
* 2008: Dynamic Shape and Appearance Modeling via Moving and Deforming Layers
* 2008: Edge descriptors for robust wide-baseline correspondence
* 2008: Editorial: CVPR 2005 Award Papers
* 2008: Filtering Internet image search results towards keyword based category recognition
* 2008: Flexible dictionaries for action classification
* 2008: Joint data alignment up to (lossy) transformations
* 2008: Localizing Objects with Smart Dictionaries
* 2008: Quick Shift and Kernel Methods for Mode Seeking
* 2008: Relaxed matching kernels for robust image comparison
* 2008: Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images
* 2008: scale of a texture and its application to segmentation, The
* 2008: Shape from Defocus via Diffusion
* 2009: Actionable information in vision
* 2009: Categorization in natural time-varying image sequences
* 2009: Class Segmentation and Object Localization with Superpixel Neighborhoods
* 2009: Hybrid Dynamical Models of Human Motion for the Recognition of Human Gaits
* 2009: Motion segmentation with occlusions on the superpixel graph
* 2009: Non-local Approach to Shape from Ambient Shading, A
* 2009: Nonlocal Similarity Image Filtering
* 2009: Nonrigid registration combining global and local statistics
* 2009: On the set of images modulo viewpoint and contrast changes
* 2009: Unsupervised multiphase segmentation: A recursive approach
* 2010: Analyzing Diving: A Dataset for Judging Action Quality
* 2010: Curious snakes: A minimum latency solution to the cluttered background problem in active contours
* 2010: Earth Mover Distance on superpixels
* 2010: Editorial for the Special Issue on Photometric Analysis for Computer Vision
* 2010: Embedded Imagers: Detecting, Localizing, and Recognizing Objects and Events in Natural Habitats
* 2010: Spike train driven dynamical models for human actions
* 2010: Texture Regimes for Entropy-Based Multiscale Image Analysis
* 2010: Tracklet Descriptors for Action Modeling and Video Analysis
* 2010: Warping background subtraction
* 2011: Detachable Object Detection with Efficient Model Selection
* 2011: Direct Sparse Deblurring
* 2011: Entropy-Scale Profiles for Texture Segmentation
* 2011: Learning and matching multiscale template descriptors for real-time detection, localization and tracking
* 2011: New Geometric Metric in the Space of Curves, and Applications to Tracking Deforming Objects by Prediction and Filtering, A
* 2011: Video-based descriptors for object recognition
* 2012: Actionable saliency detection: Independent motion detection without independent motion estimation
* 2012: Detachable Object Detection: Segmentation and Depth Ordering from Short-Baseline Video
* 2012: Discovering discriminative action parts from mid-level video representations
* 2012: Fast planar object detection and tracking via edgel templates
* 2012: Long-Range Spatio-Temporal Modeling of Video with Application to Fire Detection
* 2012: Sparse Occlusion Detection with Optical Flow
* 2012: SuperFloxels: A Mid-level Representation for Video Sequences
* 2012: Video upscaling via spatio-temporal self-similarity
* 2013: CLAM: Coupled Localization and Mapping with Efficient Outlier Handling
* 2013: Nonlinearly Constrained MRFs: Exploring the Intrinsic Dimensions of Higher-Order Cliques
* 2014: Active Frame, Location, and Detector Selection for Automated and Manual Video Annotation
* 2014: Asymmetric Sparse Kernel Approximations for Large-Scale Visual Search
* 2014: Cavlectometry: Towards Holistic Reconstruction of Large Mirror Objects
* 2014: Information-Seeking Control Under Visibility-Based Uncertainty
* 2014: Linear Systems Approach to Imaging Through Turbulence, A
* 2014: Second-Order Shape Optimization for Geometric Inverse Problems in Vision
* 2014: Volumetric reconstruction applied to perceptual studies of size and weight
* 2015: Adaptive Regularization With the Structure Tensor
* 2015: Domain-size pooling in local descriptors: DSP-SIFT
* 2015: Efficient minimal-surface regularization of perspective depth maps in variational stereo
* 2015: Multi-view feature engineering and learning
* 2015: Perspective distortion modeling, learning and compensation
* 2015: Robust Poisson Surface Reconstruction
* 2015: Self-Occlusions and Disocclusions in Causal Video Object Segmentation
* 2015: Shape Matching Using Multiscale Integral Invariants
* 2015: Texture representations for image and video synthesis
* 2016: Detecting Occlusions as an Inverse Problem
* 2016: Empirical Evaluation of Current Convolutional Architectures: Ability to Manage Nuisance Location and Scale Variability, An
* 2016: mid-level representation of visual structures for video compression, A
* 2016: Robust Surface Reconstruction
* 2016: ShapeFit and ShapeKick for Robust, Scalable Structure from Motion
* 2016: Simple Hierarchical Pooling Data Structure for Loop Closure, A
* 2017: Adaptive Discretizations for Non-smooth Variational Vision
* 2017: S2F: Slow-to-Fast Interpolator Flow
* 2017: Visual-Inertial-Semantic Scene Representation for 3D Object Detection
* 2017: Zero Shot Learning via Multi-scale Manifold Regularization
* 2018: Conditional Prior Networks for Optical Flow
* 2018: Empirical Study of the Topology and Geometry of Deep Networks
* 2018: Information Dropout: Learning Optimal Representations Through Noisy Computation
* 2018: OATM: Occlusion Aware Template Matching by Consensus Set Maximization
* 2018: Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification
* 2018: SaaS: Speed as a Supervisor for Semi-supervised Learning
* 2018: Visual-Inertial Object Detection and Mapping
* 2019: Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction
* 2019: Dense Depth Posterior (DDP) From Single Image and Sparse Range
* 2019: Few-Shot Learning With Embedded Class Models and Shot-Free Meta Training
* 2019: Finding Structure in Point Cloud Data with the Robust Isoperimetric Loss
* 2019: GeoNet: Deep Geodesic Networks for Point Cloud Analysis
* 2019: Input and Weight Space Smoothing for Semi-Supervised Learning
* 2019: Meta-Learning With Differentiable Convex Optimization
* 2019: Task2Vec: Task Embedding for Meta-Learning
* 2019: Unsupervised Domain Adaptation via Regularized Conditional Alignment
* 2019: Unsupervised Moving Object Detection via Contextual Information Separation
* 2020: Adaptive Regularization of Some Inverse Problems in Image Analysis
* 2020: Deepvoxels++: Enhancing the Fidelity of Novel View Synthesis from 3d Voxel Embeddings
* 2020: Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
* 2020: FDA: Fourier Domain Adaptation for Semantic Segmentation
* 2020: Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-output Observations
* 2020: Incremental Few-shot Meta-learning via Indirect Discriminant Alignment
* 2020: Learning to Manipulate Individual Objects in an Image
* 2020: Phase Consistent Ecological Domain Adaptation
* 2020: Spatial Class Distribution Shift in Unsupervised Domain Adaptation: Local Alignment Comes to Rescue
* 2020: Towards Backward-Compatible Representation Learning
* 2021: ARCH++: Animation-Ready Clothed Human Reconstruction Revisited
* 2021: Compatibility-aware Heterogeneous Visual Search
* 2021: DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping*
* 2021: Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning
* 2021: Learning Hierarchical Graph Neural Networks for Image Clustering
* 2021: Learning Semantic-Aware Dynamics for Video Prediction
* 2021: LQF: Linear Quadratic Fine-Tuning
* 2021: Mixed-Privacy Forgetting in Deep Networks
* 2021: Positive-Congruent Training: Towards Regression-Free Model Updates
* 2021: Unsupervised Depth Completion with Calibrated Backprojection Layers
* 2021: Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries
* 2022: Class-Incremental Learning with Strong Pre-trained Models
* 2022: MeMOT: Multi-Object Tracking with Memory
* 2022: Mixed Differential Privacy in Computer Vision
* 2022: Not Just Streaks: Towards Ground Truth for Single Image Deraining
* 2022: Omni-DETR: Omni-Supervised Object Detection with Transformers
* 2022: Stereoscopic Universal Perturbations across Different Architectures and Datasets
* 2022: Stochastic batch size for adaptive regularization in deep network optimization
* 2022: Task Adaptive Parameter Sharing for Multi-Task Learning
* 2022: X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks
* 2023: Critical Learning Periods for Multisensory Integration in Deep Networks
* 2023: Depth Estimation from Camera Image and mmWave Radar Point Cloud
* 2023: Guided Recommendation for Model Fine-Tuning
* 2023: Harnessing Unrecognizable Faces for Improving Face Recognition
* 2023: Linear Spaces of Meanings: Compositional Structures in Vision-Language Models
* 2023: Meta-Learning Approach to Predicting Performance and Data Requirements, A
* 2023: SAFE: Machine Unlearning With Shard Graphs
* 2023: Tangent Model Composition for Ensembling and Continual Fine-tuning
* 2023: Train/Test-Time Adaptation with Retrieval
* 2023: À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting
Includes: Soatto, S. Soatto, S.[Stefano]
234 for Soatto, S.
Soattoc, S.[Stefano]
* 2015: Causal video object segmentation from persistence of occlusions