Learning Extremal Representations with Deep Archetypal Analysis
Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking
A Benchmark and Evaluation of Non-Rigid Structure from Motion
Learning to Reconstruct HDR Images from Events, with Applications to Depth and Flow Prediction
Hierarchical Visual-Textual Knowledge Distillation for Life-Long Correlation Learning
Adding Knowledge to Unsupervised Algorithms for the Recognition of Intent
Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild
Evaluation of Inpainting and Augmentation for Censored Image Queries
Rectified Binary Convolutional Networks with Generative Adversarial Learning
Beyond Brightening Low-light Images
The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
Parallel Single-Pixel Imaging: A General Method for Direct–Global Separation and 3D Shape Reconstruction Under Strong Global Illumination
AutoDet: Pyramid Network Architecture Search for Object Detection
Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
A Shape Transformation-based Dataset Augmentation Framework for Pedestrian Detection
Excitation Dropout: Encouraging Plasticity in Deep Neural Networks
Benchmarking Low-Light Image Enhancement and Beyond
Label-Free Robustness Estimation of Object Detection CNNs for Autonomous Driving Applications
Incremental Rotation Averaging
Complete Singularity Analysis for the Perspective-Four-Point Problem
Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training
Comparison of Full-Reference Image Quality Models for Optimization of Image Processing Systems
Selective Wavelet Attention Learning for Single Image Deraining
A Comprehensive Benchmark Analysis of Single Image Deraining: Current Challenges and Future Perspectives
DeepFlux for Skeleton Detection in the Wild
Cross-Modal Pyramid Translation for RGB-D Scene Recognition
Deep CockTail Networks
Saliency Detection Inspired by Topological Perception Theory
OCNet: Object Context for Semantic Segmentation
MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
A Numerical Framework for Elastic Surface Matching, Comparison, and Interpolation
ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition
SODA: Weakly Supervised Temporal Action Localization Based on Astute Background Response and Self-Distillation Learning
Deep Unsupervised 3D Human Body Reconstruction from a Sparse set of Landmarks
Computer Vision and Pattern Recognition 2020
Guest Editorial: Special Issue on Deep Learning for Video Analysis and Compression
Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild
Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition
Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction
Dual-Constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior
Deep Trajectory Post-Processing and Position Projection for Single & Multiple Camera Multiple Object Tracking
Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Network
NAS-FCOS: Efficient Search for Object Detection Architectures
3D-FUTURE: 3D Furniture Shape with TextURE
DeMoCap: Low-Cost Marker-Based Motion Capture
Unsupervised Domain Adaptation in the Wild via Disentangling Representation Learning
Volume Sweeping: Learning Photoconsistency for Multi-View Shape Reconstruction
Beyond Covariance: SICE and Kernel Based Visual Feature Representation
JÂA-Net: Joint Facial Action Unit Detection and Face Alignment Via Adaptive Attention
Rain Rendering for Evaluating and Improving Robustness to Bad Weather
A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains
Face Image Reflection Removal
Unsupervised Deep Representation Learning for Real-Time Tracking
Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings
LaSOT: A High-quality Large-scale Single Object Tracking Benchmark
Benchmarking the Robustness of Semantic Segmentation Models with Respect to Common Corruptions
Fine-Grained Instance-Level Sketch-Based Image Retrieval
Binarized Neural Architecture Search for Efficient Object Recognition
Image Matching Across Wide Baselines: From Paper to Practice
HOTA: A Higher Order Metric for Evaluating Multi-object Tracking
Deformable Kernel Networks for Joint Image Filtering
View Transfer on Human Skeleton Pose: Automatically Disentangle the View-Variant and View-Invariant Information for Pose Representation Learning
Image Matching from Handcrafted to Deep Features: A Survey
A Camera Model for Line-Scan Cameras with Telecentric Lenses
Solving Rolling Shutter 3D Vision Problems using Analogies with Non-rigidity
Temporally Coherent General Dynamic Scene Reconstruction
Recursive Context Routing for Object Detection
Scene Text Detection and Recognition: The Deep Learning Era
Improving Image Description with Auxiliary Modality for Visual Localization in Challenging Conditions
DeepVS2.0: A Saliency-Structured Deep Learning Method for Predicting Dynamic Visual Attention
Pixel-Wise Crowd Understanding via Synthetic Data
Talk2Nav: Long-Range Vision-and-Language Navigation with Dual Attention and Spatial Memory
Guest Editorial: Special Issue on Performance Evaluation in Computer Vision
Guest Editorial: Special Issue on “Computer Vision for All Seasons: Adverse Weather and Lighting Conditions”
Segmentation by Continuous Latent Semantic Analysis for Multi-structure Model Fitting
A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videos
CNN-Based RGB-D Salient Object Detection: Learn, Select, and Fuse
Quo Vadis, Skeleton Action Recognition?
Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks
VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change
Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset
The Isowarp: The Template-Based Visual Geometry of Isometric Surfaces
Scale-Aware Domain Adaptive Faster R-CNN
Unsupervised Domain Adaptation with Background Shift Mitigating for Person Re-Identification
Synthetic Humans for Action Recognition from Unseen Viewpoints
Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer
Knowledge Distillation: A Survey
Learning Deep Patch representation for Probabilistic Graphical Model-Based Face Sketch Synthesis
Development and Validation of an Unsupervised Feature Learning System for Leukocyte Characterization and Classification: A Multi-Hospital Study
Vote-Based 3D Object Detection with Context Modeling and SOB-3DNMS
Guided Attention in CNNs for Occluded Pedestrian Detection and Re-identification
Visual Structure Constraint for Transductive Zero-Shot Learning in the Wild
Polysemy Deciphering Network for Robust Human–Object Interaction Detection
Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning
Object Priors for Classifying and Localizing Unseen Actions
Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection
Deep Human-Interaction and Association by Graph-Based Learning for Multiple Object Tracking in the Wild
Renormalization for Initialization of Rolling Shutter Visual-Inertial Odometry
Progressive Multi-granularity Analysis for Video Prediction
Residual Dual Scale Scene Text Spotting by Fusing Bottom-Up and Top-Down Processing
Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild
Entrack: Probabilistic Spherical Regression with Entropy Regularization for Fiber Tractography
Weakly Supervised Group Mask Network for Object Detection
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
Viewpoint and Scale Consistency Reinforcement for UAV Vehicle Re-Identification
Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition Under Occlusion
CDTD: A Large-Scale Cross-Domain Benchmark for Instance-Level Image-to-Image Translation and Domain Adaptive Object Detection
Deep Nets: What have They Ever Done for Vision?
Correction to: Rooted Spanning Superpixels
Deformable Image Registration Based on Functions of Bounded Generalized Deformation
Adaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters
Towards Balanced Learning for Instance Recognition
Letter-Level Online Writer Identification
Manhattan Room Layout Reconstruction from a Single \(360^{\circ }\) Image: A Comparative Study of State-of-the-Art Methods
ACTNET: End-to-End Learning of Feature Activations and Multi-stream Aggregation for Effective Instance Image Retrieval
Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis
LAMP-HQ: A Large-Scale Multi-pose High-Quality Database and Benchmark for NIR-VIS Face Recognition
Spatial–Temporal Relation Reasoning for Action Prediction in Videos
Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation
Visual Interestingness Prediction: A Benchmark Framework and Literature Review
EfficientPS: Efficient Panoptic Segmentation
Intra-Camera Supervised Person Re-Identification
Enhanced 3D Human Pose Estimation from Videos by Using Attention-Based Neural Network with Dilated Convolutions
An Exploration of Embodied Visual Exploration
Context-Enhanced Representation Learning for Single Image Deraining
Mimetics: Towards Understanding Human Actions Out of Context
Successive Graph Convolutional Network for Image De-raining
Evaluation Metrics for Conditional Image Generation
Evaluating Visual Properties via Robust HodgeRank
You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network
Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
Correction to: Parallel Single-Pixel Imaging: A General Method for Direct–Global Separation and 3D Shape Reconstruction Under Strong Global Illumination
Deep Learning Geometry Compression Artifacts Removal for Video-Based Point Cloud Compression
A Coarse-to-Fine Framework for Resource Efficient Video Recognition
Predicting Visual Political Bias Using Webly Supervised Data and an Auxiliary Task
Guest Editorial: Special Issue: Computer Vision and Pattern Recognition (DAGM GCPR 2019)
3D Scene Reconstruction with an Un-calibrated Light Field Camera
Hierarchical Conditional Relation Networks for Multimodal Video Question Answering
BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking
Assignment Flow for Order-Constrained OCT Segmentation
The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation
Semantic Bottlenecks: Quantifying and Improving Inspectability of Deep Representations
Norm-Aware Embedding for Efficient Person Search and Tracking
Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition
Spectral Shape Recovery and Analysis Via Data-driven Connections
SDNet: A Versatile Squeeze-and-Decomposition Network for Real-Time Image Fusion
Pluralistic Free-Form Image Completion
A Decomposable Winograd Method for N–D Convolution Acceleration in Video Analysis
Deep Maximum a Posterior Estimator for Video Denoising
SportsCap: Monocular 3D Human Motion Capture and Fine-Grained Understanding in Challenging Sports Videos
DLOW: Domain Flow and Applications
Just Recognizable Distortion for Machine Vision Oriented Image and Video Coding
Adaptive Dimension-Discriminative Low-Rank Tensor Recovery for Computational Hyperspectral Imaging
Context and Structure Mining Network for Video Object Detection
Multi-level Motion Attention for Human Motion Prediction
Learning Regression and Verification Networks for Robust Long-term Tracking
Unsupervised Scale-Consistent Depth Learning from Video
Learned Collaborative Stereo Refinement
Tracking by Deblatting
Semantics-to-Signal Scalable Image Compression with Learned Revertible Representations
Structure-Measure: A New Way to Evaluate Foreground Maps
Towards High Performance Human Keypoint Detection
Learning to Caricature via Semantic Shape Transform
Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation
Learning Adaptive Attribute-Driven Representation for Real-Time RGB-T Tracking
Correction to: Long-Short Temporal–Spatial Clues Excited Network for Robust Person Re-identification
