International Journal of Computer Vision

Article	Citations
Knowledge Distillation: A Survey	979
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking	595
BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation	565
Image Matching from Handcrafted to Deep Features: A Survey	495
HOTA: A Higher Order Metric for Evaluating Multi-object Tracking	326
Learning to Prompt for Vision-Language Models	324
Beyond Brightening Low-light Images	265
Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation	254
Scene Text Detection and Recognition: The Deep Learning Era	216
Image Matching Across Wide Baselines: From Paper to Practice	174
SDNet: A Versatile Squeeze-and-Decomposition Network for Real-Time Image Fusion	173
Human Action Recognition and Prediction: A Survey	171
The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection	154
Weakly-supervised Semantic Guided Hashing for Social Image Retrieval	141
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking	137
Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset	131
OCNet: Object Context for Semantic Segmentation	123
EfficientPS: Efficient Panoptic Segmentation	119
You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network	109
Benchmarking Low-Light Image Enhancement and Beyond	107
Deep Image Deblurring: A Survey	99
Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100	98
Unsupervised Scale-Consistent Depth Learning from Video	91
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection	87
Comparison of Full-Reference Image Quality Models for Optimization of Image Processing Systems	85

Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis	84
Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images	83
Pixel-Wise Crowd Understanding via Synthetic Data	75
LaSOT: A High-quality Large-scale Single Object Tracking Benchmark	75
On the Arbitrary-Oriented Object Detection: Classification Based Approaches Revisited	74
Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training	73
Unsupervised Deep Representation Learning for Real-Time Tracking	71
JÂA-Net: Joint Facial Action Unit Detection and Face Alignment Via Adaptive Attention	69
Curriculum Learning: A Survey	65
A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains	62
Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis	62
Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild	59
GhostNets on Heterogeneous Devices via Cheap Operations	54
CLIP-Adapter: Better Vision-Language Models with Feature Adapters	54
Deformable Kernel Networks for Joint Image Filtering	53
Explainability of Deep Vision-Based Autonomous Driving Systems: Review and Challenges	53
Structure-Measure: A New Way to Evaluate Foreground Maps	52
Adaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters	52
VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change	51
Learning Adaptive Attribute-Driven Representation for Real-Time RGB-T Tracking	50
ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond	50
AutoScale: Learning to Scale for Crowd Counting	50
Rain Rendering for Evaluating and Improving Robustness to Bad Weather	48
3D-FUTURE: 3D Furniture Shape with TextURE	47
An Exploration of Embodied Visual Exploration	45
Occluded Video Instance Segmentation: A Benchmark	44
Synthetic Humans for Action Recognition from Unseen Viewpoints	43
Towards High Performance Human Keypoint Detection	43
Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition Under Occlusion	41
Vis-MVSNet: Visibility-Aware Multi-view Stereo Network	41
The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation	41
A Comprehensive Benchmark Analysis of Single Image Deraining: Current Challenges and Future Perspectives	41
Scale-Aware Domain Adaptive Faster R-CNN	40
A Survey on Long-Tailed Visual Recognition	40
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild	39
Train Sparsely, Generate Densely: Memory-Efficient Unsupervised Training of High-Resolution Temporal GAN	39
Countering Malicious DeepFakes: Survey, Battleground, and Horizon	39
Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning	37
Bridging Composite and Real: Towards End-to-End Deep Image Matting	35
NormAttention-PSN: A High-frequency Region Enhanced Photometric Stereo Network with Normalized Attention	35
Deep Nets: What have They Ever Done for Vision?	35
Multi-level Motion Attention for Human Motion Prediction	34
SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds	33
Zero-Shot Object Detection: Joint Recognition and Localization of Novel Concepts	33
Context Autoencoder for Self-supervised Representation Learning	33
Twin Contrastive Learning for Online Clustering	33
Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild	32
Learning to Reconstruct HDR Images from Events, with Applications to Depth and Flow Prediction	32
Quo Vadis, Skeleton Action Recognition?	32
Semantic Edge Detection with Diverse Deep Supervision	32

Viewpoint and Scale Consistency Reinforcement for UAV Vehicle Re-Identification	31
Successive Graph Convolutional Network for Image De-raining	31
3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation	30
Mimetics: Towards Understanding Human Actions Out of Context	29
Compositional GAN: Learning Image-Conditional Binary Composition	28
Benchmarking the Robustness of Semantic Segmentation Models with Respect to Common Corruptions	28
Manhattan Room Layout Reconstruction from a Single $$360^{\circ }$$ Image: A Comparative Study of State-of-the-Art Methods	28
Polysemy Deciphering Network for Robust Human–Object Interaction Detection	27
Recursive Context Routing for Object Detection	27
MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation	27
Low-light Image Enhancement via Breaking Down the Darkness	27
Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks	27
Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction	27
Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization	27
LAMP-HQ: A Large-Scale Multi-pose High-Quality Database and Benchmark for NIR-VIS Face Recognition	26
SportsCap: Monocular 3D Human Motion Capture and Fine-Grained Understanding in Challenging Sports Videos	26
Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer	26
A Coarse-to-Fine Framework for Resource Efficient Video Recognition	24
Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild	24
Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior	23
Hadamard Matrix Guided Online Hashing	23
Semantics-to-Signal Scalable Image Compression with Learned Revertible Representations	23
Selective Wavelet Attention Learning for Single Image Deraining	23
Multi-task Compositional Network for Visual Relationship Detection	22
Parallel Single-Pixel Imaging: A General Method for Direct–Global Separation and 3D Shape Reconstruction Under Strong Global Illumination	22
Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization	22
Fine-Grained Instance-Level Sketch-Based Image Retrieval	22
Dual Convolutional Neural Networks for Low-Level Vision	22
Unsupervised Domain Adaptation with Background Shift Mitigating for Person Re-Identification	22
Feature Matching via Motion-Consistency Driven Probabilistic Graphical Model	21
Talk2Nav: Long-Range Vision-and-Language Navigation with Dual Attention and Spatial Memory	21
RePCD-Net: Feature-Aware Recurrent Point Cloud Denoising Network	21
Memory-Augmented Deep Unfolding Network for Guided Image Super-resolution	20
3D Semantic Scene Completion: A Survey	20
SODA: Weakly Supervised Temporal Action Localization Based on Astute Background Response and Self-Distillation Learning	20
Context-Enhanced Representation Learning for Single Image Deraining	19
Learning Deep Patch representation for Probabilistic Graphical Model-Based Face Sketch Synthesis	19
Zero-Shot Learning on 3D Point Cloud Objects and Beyond	19
SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World	19
Underwater Camera: Improving Visual Perception Via Adaptive Dark Pixel Prior and Color Correction	19
Spatial–Temporal Relation Reasoning for Action Prediction in Videos	19
Adaptive Deep Disturbance-Disentangled Learning for Facial Expression Recognition	18
Joint Classification and Regression for Visual Tracking with Fully Convolutional Siamese Networks	18
3D Object Detection for Autonomous Driving: A Comprehensive Survey	18
Intra-Camera Supervised Person Re-Identification	18
Dual-Constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior	18
A Shape Transformation-based Dataset Augmentation Framework for Pedestrian Detection	18
Dual-Attention-Guided Network for Ghost-Free High Dynamic Range Imaging	18
REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets	17
Towards Balanced Learning for Instance Recognition	17
Enhanced 3D Human Pose Estimation from Videos by Using Attention-Based Neural Network with Dilated Convolutions	17
Learning Self-supervised Low-Rank Network for Single-Stage Weakly and Semi-supervised Semantic Segmentation	17
Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition	17
Incorporating Side Information by Adaptive Convolution	17
A General Framework for Deep Supervised Discrete Hashing	17
Delving Deeper into Anti-Aliasing in ConvNets	17
On Measuring and Controlling the Spectral Bias of the Deep Image Prior	16
Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision	16
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling	16
Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection	16
PhysFormer++: Facial Video-Based Physiological Measurement with SlowFast Temporal Difference Transformer	16
Learning to Detect Instance-Level Salient Objects Using Complementary Image Labels	16
Class-Difficulty Based Methods for Long-Tailed Visual Recognition	15
SliderGAN: Synthesizing Expressive Face Images by Sliding 3D Blendshape Parameters	15
OASIS: Only Adversarial Supervision for Semantic Image Synthesis	15
Learning Regression and Verification Networks for Robust Long-term Tracking	15
Vote-Based 3D Object Detection with Context Modeling and SOB-3DNMS	15
A Survey on Intrinsic Images: Delving Deep into Lambert and Beyond	15
Evaluation Metrics for Conditional Image Generation	15
One-Shot Object Affordance Detection in the Wild	15
Residual Dual Scale Scene Text Spotting by Fusing Bottom-Up and Top-Down Processing	15
Label-Free Robustness Estimation of Object Detection CNNs for Autonomous Driving Applications	14
Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-Based Image Retrieval	14
Beyond Covariance: SICE and Kernel Based Visual Feature Representation	14
DeMoCap: Low-Cost Marker-Based Motion Capture	14
Revisiting Consistency Regularization for Semi-Supervised Learning	14
ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition	14
Pre-Training Without Natural Images	14
RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning	14
Learning the Clustering of Longitudinal Shape Data Sets into a Mixture of Independent or Branching Trajectories	14

Face Image Reflection Removal	14
Guided Attention in CNNs for Occluded Pedestrian Detection and Re-identification	14
I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-Shaped Scene Text Detection	13
A Benchmark and Evaluation of Non-Rigid Structure from Motion	13
Object Priors for Classifying and Localizing Unseen Actions	13
RoCGAN: Robust Conditional GAN	13
CDTD: A Large-Scale Cross-Domain Benchmark for Instance-Level Image-to-Image Translation and Domain Adaptive Object Detection	13
EAN: Event Adaptive Network for Enhanced Action Recognition	13
Sparse Black-Box Video Attack with Reinforcement Learning	13
Unsupervised Domain Adaptation in the Wild via Disentangling Representation Learning	13
Delving into Inter-Image Invariance for Unsupervised Visual Representations	13
Going Deeper than Tracking: A Survey of Computer-Vision Based Recognition of Animal Pain and Emotions	12
AutoDet: Pyramid Network Architecture Search for Object Detection	12
Pyramid Attention Network for Image Restoration	12
Saliency Detection Inspired by Topological Perception Theory	12
Attribute Prototype Network for Any-Shot Learning	12
Visual Object Tracking in First Person Vision	12
A Numerical Framework for Elastic Surface Matching, Comparison, and Interpolation	12
Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation	12
H-SegMed: A Hybrid Method for Prostate Segmentation in TRUS Images via Improved Closed Principal Curve and Improved Enhanced Machine Learning	12
Artificial Intelligence for Dunhuang Cultural Heritage Protection: The Project and the Dataset	12