Kweon, H.[Hyeokjun]
Co Author Listing * Adversarial Erasing Framework via Triplet with Gated Pyramid Pooling Layer for Weakly Supervised Semantic Segmentation
* Assessing the Applicability of Mobile Laser Scanning for Mapping Forest Roads in the Republic of Korea
* Unlocking the Potential of Ordinary Classifier: Class-specific Adversarial Erasing Framework for Weakly Supervised Semantic Segmentation
* Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor
Includes: Kweon, H.[Hyeokjun] Kweon, H.[Hyeongkeun]
Kweon, H.J.[Hyeok Joon]
Co Author Listing * Cloth-Changing Person Re-Identification With Noisy Patch Filtering
Includes: Kweon, H.J.[Hyeok Joon] Kweon, H.J.[Hyeok-Joon]
Kweon, I.
Co Author Listing * 3-D Vision for Outdoor Navigation by an Autonomous Vehicle
* 3-D Vision Techniques for Autonomous Vehicles
* Globally optimal line clustering and vanishing point estimation in Manhattan world
* High-Resolution Terrain Map from Multiple Sensor Data
* Specular Reflection Separation Using Dark Channel Prior
Includes: Kweon, I. Kweon, I.[Inso]
Kweon, I.S.[In So]
Co Author Listing * email: Kweon, I.S.[In So]: iskweon77 AT kaist ac kr
* 2-D Object Recognition Using Invariant Contour Descriptor and Projective Refinement
* 2D/3D virtual face modeling
* 3-D object recognition using a new invariant relationship by single-view
* 3D Display Calibration by Visual Pattern Analysis
* 3D structure recovery and calibration under varying intrinsic parameters using known angles
* 3D target recognition using cooperative feature map binding under Markov Chain Monte Carlo
* 6-DOF Direct Homography Tracking with Extended Kalman Filter
* Accelerated Kmeans Clustering Using Binary Random Projection
* Accurate 3D Reconstruction from Small Motion Clip for Rolling Shutter Cameras
* Accurate Camera Calibration Robust to Defocus Using a Smartphone
* Accurate depth map estimation from a lenslet light field camera
* ACP++: Action Co-Occurrence Priors for Human-Object Interaction Detection
* Adaptive Support-Weight Approach for Correspondence Search
* All-Around Depth from Small Motion with a Spherical Panoramic Camera
* Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing, The
* Appearance-Cloning: Photo-Consistent Scene Recovery from Multi-View Images
* Artrieval: Painting retrieval without expert knowledge
* AttentionNet: Aggregating Weak Directions for Accurate Object Detection
* Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation
* Automated checkerboard detection and indexing using circular boundaries
* Automatic closed eye correction
* Automatic Content-Aware Color and Tone Stylization
* Automatic edge detection using 3X3 ideal binary pixel patterns and fuzzy-based edge thresholding
* Automatic model-based 3D object recognition by combining feature matching with tracking
* Automatic Trimap Generation and Consistent Matting for Light-Field Images
* Autonomous Driving System for Unknown Environments Using a Unified Map, An
* Background Robust Object Labeling by Voting of Weight-Aggregated Local Features
* Balanced optical flow refinement by bidirectional constraint
* Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspective
* Biologically Motivated Perceptual Feature: Generalized Robust Invariant Feature
* Biprism-Stereo Camera System, A
* Branch-and-Bound Approach to Correspondence and Grouping Problems, A
* Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection
* Calibrating a Non-isotropic Near Point Light Source Using a Plane
* Camera calibration based on arbitrary parallelograms
* Camera calibration system using planar concentric circles and method thereof
* Capturing Village-Level Heritages with a Hand-held Camera-Laser Fusion Sensor
* Category-specific upright orientation estimation for 3D model classification and retrieval
* CBAM: Convolutional Block Attention Module
* CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution
* Change detection using a statistical model in an optimally selected color space
* Closed-Form Solution to Rotation Estimation for Structure from Small Motion, A
* Color and Printer Models for Color Half Toning
* Color indexing using chromatic invariant
* Color linear model
* Color Transfer Using Probabilistic Moving Least Squares
* Complementary Sets of Shutter Sequences for Motion Deblurring
* Consistent Matting for Light Field Images
* Contextual Bag-of-Words for Visual Categorization
* Contextual decomposition of multi-label images
* Contextually Customized Video Summaries Via Natural Language
* ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
* COP: a new corner detector
* COP: A new method for extracting edges and corners
* Correspondence Search in the Presence of Specular Highlights Using Specular-Free Two-Band Images
* Cost-aware depth map estimation for Lytro camera
* Crosswalk and traffic light detection via integral framework
* DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning
* Data-free Universal Adversarial Perturbation and Black-box Attack
* Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation
* Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness
* Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence
* Deep Convolutional Neural Network for Natural Image Matting Using Initial Alpha Mattes
* Deep Depth Estimation from Thermal Image
* Deep Depth from Uncalibrated Small Motion Clip
* Deep Video Inpainting
* DeepPTZ: Deep Self-Calibration for PTZ Cameras
* Deltille Grids for Geometric Camera Calibration
* Dense Pixel-Level Interpretation of Dynamic Scenes With Video Panoptic Segmentation
* Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
* Dense Relational Image Captioning via Multi-Task Triple-Stream Networks
* Depth Completion using Plane-Residual Representation
* Depth from a Light Field Image with Learning-Based Matching Costs
* Depth from accidental motion using geometry prior
* Detecting Human-object Interactions with Action Co-occurrence Priors
* Determination of Color Space for Accurate Change Detection
* Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation, The
* Dichromatic-Based Color Constancy Using Dichromatic Slope and Dichromatic Line Space
* Difference-Based Image Noise Modeling Using Skellam Distribution
* DIFRINT: Deep Iterative Frame Interpolation for Full-Frame Video Stabilization
* Disjoint Multi-task Learning Between Heterogeneous Human-Centric Tasks
* Distinctive Similarity Measure for stereo matching under point ambiguity
* Distort-and-Recover: Color Enhancement Using Deep Reinforcement Learning
* Double Targeted Universal Adversarial Perturbations
* Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo
* EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization
* edge-based algorithm for discontinuity adaptive color image smoothing, An
* Efficient adaptive non-maximal suppression algorithms for homogeneous spatial keypoint distribution
* Efficient and Robust Color Consistency for Community Photo Collections
* Empirical study on using adapters for debiased Visual Question Answering
* EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Images
* Estimating Intrinsic Parameters of Cameras using Two Arbitrary Rectangles
* Euclidean Structure from Confocal Conics: Theory and Application to Camera Calibration
* Event-Specific Audio-Visual Fusion Layers: A Simple and New Perspective on Video Understanding
* Exploiting Shading Cues in Kinect IR Images for Geometry Refinement
* Extracting Topographic Terrain Features from Elevation Maps
* Extraction of Line Features in a Noisy Image
* Facial Depth and Normal Estimation Using Single Dual-Pixel Camera
* Fast Central Catadioptric Line Extraction
* Fast object recognition using dynamic programming from combination of salient line groups
* Fast Randomized Singular Value Thresholding for Low-Rank Optimization
* Fast randomized Singular Value Thresholding for Nuclear Norm Minimization
* Fast Separation of Reflection Components using a Specularity-Invariant Image Representation
* Fine-Scale Surface Normal Estimation Using a Single NIR Image
* Fluttering Pattern Generation Using Modified Legendre Sequence for Coded Exposure Imaging
* Fusing Multiple Independent Estimates via Spectral Clustering for Robust Visual Tracking
* Gated bidirectional feature pyramid network for accurate one-shot detection
* Generating Fluttering Patterns with Low Autocorrelation for Coded Exposure Imaging
* Generative Bias for Robust Visual Question Answering
* Geometric and Algebraic Constraints of Projected Concentric Circles and Their Applications to Camera Calibration
* Geometric Calibration of Micro-Lens-Based Light Field Cameras Using Line Features
* Geometry Guided Three-Dimensional Propagation for Depth From Small Motion
* Global-and-local Relative Position Embedding for Unsupervised Video Summarization
* Globally Optimal Inlier Set Maximization for Atlanta Frame Estimation
* Globally Optimal Inlier Set Maximization for Atlanta World Understanding
* Globally Optimal Manhattan Frame Estimation in Real-Time
* GMM-based saliency aggregation for calibration-free gaze estimation
* Gradient-Based Camera Exposure Control for Outdoor Mobile Platforms
* Graph-based shape matching for deformable objects
* Hierarchical 3D line restoration based on angular proximity in structured environments
* Hierarchical on-line boosting based background subtraction
* High dynamic range imaging by a rank-1 constraint
* High quality depth map upsampling for 3D-TOF cameras
* High Quality Shape from a Single RGB-D Image under Uncalibrated Natural Illumination
* High Quality Structure from Small Motion for Rolling Shutter Cameras
* High-Quality Depth from Uncalibrated Small Motion Clip
* High-Quality Depth Map Upsampling and Completion for RGB-D Cameras
* High-quality Frame Interpolation via Tridirectional Inference
* How human visual systems recognize objects: A Novel Computational Model
* Human perception based color image quantization
* Identigram/watermark removal using cross-channel correlation
* Illuminant Direction and Shape of a Bump
* Image Decomposition With Multilabel Context: Algorithms and Applications
* Image-Optimized Rolling Cache: Reducing the Miss Penalty for Memory-Intensive Vision Algorithms
* Improvement of feature matching in catadioptric images using gyroscope data
* Infinite Homography Estimation Using Two Arbitrary Planar Rectangles
* Intelligent Assistant for People with Low Vision Abilities
* Investigating Top-k White-Box and Transferable Black-box Attack
* Iterative Method for Improving Bas-relief Ambiguity, An
* KAIST Multi-Spectral Day/Night Data Set for Autonomous and Assisted Driving
* KSL-Guide: A Large-scale Korean Sign Language Dataset Including Interrogative Sentences for Guiding the Deaf and Hard-of-Hearing
* LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation
* Large object detection in cluttered background using boosted Markov Chain Monte Carlo
* Large-Scale Virtual Dataset and Egocentric Localization for Disaster Responses, A
* Learning a Deep Convolutional Network for Light-Field Image Super-Resolution
* Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation
* Learning Image Representations by Completing Damaged Jigsaw Puzzles
* Learning Loss for Active Learning
* Learning Optimal Compact Codebook for Efficient Object Categorization
* Learning to Associate Every Segment for Video Panoptic Segmentation
* Learning to Localize Sound Source in Visual Scenes
* Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications
* Less Can Be More: Sound Source Localization With a Classification Model
* Light-Field Image Super-Resolution Using Convolutional Neural Network
* Line meets as-projective-as-possible image stitching with moving DLT
* Linear RGB-D SLAM for Structured Environments
* Locally Adaptive Support-Weight Approach for Visual Correspondence Search
* Long-range Multimodal Pretraining for Movie Understanding
* Long-term Video Frame Interpolation via Feature Propagation
* MAP-Based probabilistic reasoning to vehicle segmentation
* Mask-Guided Matting in the Wild
* MATE: Masked Autoencoders are Online 3D Test-Time Learners
* MC-Calib: A generic and robust calibration toolbox for multi-camera systems
* Measuring conceptual relation of visual words for visual categorization
* Method and apparatus for omni-directional image and 3-dimensional data acquisition with data annotation and dynamic range extension method
* Metric reconstruction of planes utilizing off-the-plane features
* ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation
* MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
* Modeling photo composition and its application to photo re-arrangement
* Motion estimation by decoupling rotation and translation in catadioptric vision
* MS2Net: Multi-Scale and Multi-Stage Feature Fusion for Blurred Image Super-Resolution
* Multi-Image Deblurring Using Complementary Sets of Fluttering Patterns
* Multi-modal Sequential Monte Carlo for On-Line Hierarchical Graph Structure Estimation in Model-based Scene Interpretation
* Multi-scale pyramid pooling for deep convolutional representation
* Multi-View Object Extraction With Fractional Boundaries
* Multispectral pedestrian detection: Benchmark dataset and baseline
* Multiview Photometric Stereo Using Planar Mesh Parameterization
* Natural Image Matting Using Deep Convolutional Neural Networks
* Noise Robust Depth from Focus Using a Ring Difference Filter
* Non-local Spatial Propagation Network for Depth Completion
* Object Categorization Robust to Surface Markings using Entropy-guided Codebook
* Object Recognition Using a Generalized Robust Invariant Feature and Gestalt's Law of Proximity and Similarity
* One-Day Outdoor Photometric Stereo Using Skylight Estimation
* One-day outdoor photometric stereo via skylight estimation
* Part-Based Player Identification Using Deep Convolutional Representation and Multi-scale Pooling
* Partial Sum Minimization of Singular Values in Robust PCA: Algorithm and Applications
* Partial Sum Minimization of Singular Values in RPCA for Low-Level Vision
* Particle Filter Approach Adapted to Catadioptric Images for Target Tracking Application
* Per-Clip Video Object Segmentation
* Personalized Cinemagraphs Using Semantic Understanding and Collaborative Learning
* Photometric Stereo Under Non-uniform Light Intensities and Exposures
* Pixel-Level Domain Transfer
* Pixel-Level Matching for Video Object Segmentation Using Convolutional Neural Networks
* PointMixer: MLP-Mixer for Point Cloud Understanding
* Probabilistic Derivative Measure Based on the Distribution of Intensity Difference, A
* Probabilistic matching of line segments for their homography
* Probabilistic matching of lines for their homography
* Probabilistic moving least squares with spatial constraints for nonlinear color transfer between images
* Propose-and-Attend Single Shot Detector
* Pushing the Envelope of Modern Methods for Bundle Adjustment
* Radiometric Calibration by Rank Minimization
* Radiometric calibration by transform invariant low-rank structure
* Rao-Blackwellized particle filtering with Gaussian mixture models for robust visual tracking
* Real-Time and Energy-Efficient Embedded System for Intelligent ADAS with RNN-Based Deep Risk Prediction using Stereo Camera, A
* Real-Time Head Orientation from a Monocular Camera Using Deep Neural Network
* Real-time motion detection based on Discrete Cosine Transform
* Real-Time Multi-Car Localization and See-Through System
* Real-Time Vehicular Vision System to Seamlessly See-Through Cars, A
* Rectangle Extraction in Catadioptric Images
* Recurrent Temporal Aggregation Framework for Deep Video Inpainting
* Reducing ambiguity in feature point matching by preserving local geometric consistency
* Refining Geometry from Depth Sensors using IR Shading Images
* Reflection removal using disparity and gradient-sparsity via smoothing algorithm
* Relative scale estimation between two camera motions
* ResNet or DenseNet? Introducing Dense Shortcuts to ResNet
* Restoration of Video Frames from a Single Blurred Image with Motion Understanding
* Revisiting Batch Normalization for Improving Corruption Robustness
* Ring Difference Filter for Fast and Noise Robust Depth From Focus
* Robust and direct estimation of 3-D motion and scene depth from stereo image sequences
* Robust and Efficient Estimation of Relative Pose for Cameras on Selfie Sticks
* Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time
* Robust Binary Feature Using the Intensity Order
* Robust Computer Vision Techniques for High-Quality 3D Modeling
* Robust Depth Estimation from Auto Bracketed Images
* Robust Depth Estimation Using Auto-Exposure Bracketing
* Robust direct motion estimation considering discontinuity
* Robust feature point matching by preserving local geometric consistency
* Robust High Dynamic Range Imaging by Rank Minimization
* Robust model-based scene interpretation by multilayered context information
* Robust Multiview Photometric Stereo Using Planar Mesh Parameterization
* Robust Reference-Based Super-Resolution With Similarity-Aware Deformable Convolution
* Robust Road Marking Detection and Recognition Using Density-Based Grouping and Machine Learning Techniques
* Scalable Representation and Learning for 3D Object Recognition Using Shared Feature-Based View Clustering
* Scalable representation for 3D object recognition using feature sharing and view clustering
* Scene Interpretation: Unified Modeling of Visual Context by Particle-Based Belief Propagation in Hierarchical Graphical Model
* Self-Supervised Monocular Depth and Motion Learning in Dynamic Scenes: Semantic Prior to Rescue
* Self-supervised Monocular Depth Estimation from Thermal Images via Adversarial Multi-spectral Adaptation
* Semantic-guided de-attention with sharpened triplet marginal loss for visual place recognition
* Semi-Calibrated Photometric Stereo
* Semi-metric Space: A New Approach to Treat Orthogonality and Parallelism
* Sensor noise modeling using the Skellam distribution: Application to the color edge detection
* Simple and Light-Weight Attention Module for Convolutional Neural Networks, A
* Simultaneous Classification and Visual Word Selection using Entropy-based Minimum Description Length
* Simultaneous Estimation of Near IR BRDF and Fine-Scale Surface Geometry
* Simultaneous place and object recognition using collaborative context information
* Simultaneous Plane Extraction and 2D Homography Estimation Using Local Feature Transformations
* Single Lens Stereo with a Biprism
* Single View Scene Scale Estimation using Scale Field
* Spacetime Surface Regularization for Neural Dynamic Scene Reconstruction
* Spherical Region-Based Matching of Vanishing Points in Catadioptric Images
* StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection
* Stereo Matching with Color and Monochrome Cameras in Low-Light Conditions
* Stereo Matching with Symmetric Cost Functions
* Stereo Matching with the Distinctive Similarity Measure
* superpixel MRF approach using high-order likelihood for moving object detection, A
* Support Aggregation via Non-linear Diffusion with Disparity-Dependent Support-Weights for Stereo Matching
* Synergistic Place and Object Recognition using Bidirectional Context Information
* System-on-Chip Solution of Video Stabilization for CMOS Image Sensors in Hand-Held Devices
* Taxonomy and Evaluation of Dense Light Field Depth Estimation Algorithms, A
* Tensor Voting Approach for Multi-View 3D Scene Flow Estimation and Refinement, A
* Tensor-Based Algorithm for High-Order Graph Matching, A
* Time-of-Flight Sensor Calibration for a Color and Depth Camera Pair
* Tracking by Associating Clips
* TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation
* TubeFormer-DeepLab: Video Mask Transformer
* Two Phase Approach for Pedestrian Detection, A
* Two-phase approach for multi-view object extraction
* Two-phase Pseudo Label Densification for Self-training Based Domain Adaptation
* UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation
* Understanding Adversarial Examples From the Mutual Influence of Images and Perturbations
* Unified Approach of Multi-scale Deep and Hand-Crafted Features for Defocus Estimation, A
* Unsupervised Intra-Domain Adaptation for Semantic Segmentation Through Self-Supervision
* Variational Prototyping-Encoder: One-Shot Learning With Prototypical Images
* Video Panoptic Segmentation
* Video-Story Composition via Plot Analysis
* VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction
* Voting-based separation of diffuse and specular pixels
* VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition
* Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting
Includes: Kweon, I.S.[In So] Kweon, I.S. Kweon, I.S.[In-So]
280 for Kweon, I.S.
Kweon, J.H.
Co Author Listing * Boundary Block-Merging (BBM) Technique for Efficient Texture Coding of Arbitrarily Shaped Object
* Method and apparatus for predictively coding shape information of video signal
Includes: Kweon, J.H. Kweon, J.H.[Ji Heon]
Kweon, S.K.
Co Author Listing * Estimation of Soil Moisture and Surface Roughness From Single-Polarized Radar Data for Bare Soil Surface and Comparison With Dual- and Quad-Polarization Cases
* Modified Water-Cloud Model With Leaf Angle Parameters for Microwave Backscattering From Agricultural Fields, A
Includes: Kweon, S.K. Kweon, S.K.[Soon-Koo]