International Journal of Computer Vision

Article	Citations
Knowledge Distillation: A Survey	1047
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking	634
BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation	609
Image Matching from Handcrafted to Deep Features: A Survey	516
Learning to Prompt for Vision-Language Models	360
HOTA: A Higher Order Metric for Evaluating Multi-object Tracking	357
Beyond Brightening Low-light Images	293
Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation	268
Scene Text Detection and Recognition: The Deep Learning Era	222
SDNet: A Versatile Squeeze-and-Decomposition Network for Real-Time Image Fusion	186
Human Action Recognition and Prediction: A Survey	184
Image Matching Across Wide Baselines: From Paper to Practice	181
The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection	162
Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset	144
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking	144
Weakly-supervised Semantic Guided Hashing for Social Image Retrieval	143
OCNet: Object Context for Semantic Segmentation	132
EfficientPS: Efficient Panoptic Segmentation	123
You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network	116
Benchmarking Low-Light Image Enhancement and Beyond	113
Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100	111
Deep Image Deblurring: A Survey	109
Comparison of Full-Reference Image Quality Models for Optimization of Image Processing Systems	96
Unsupervised Scale-Consistent Depth Learning from Video	96
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection	92

Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis	88
Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images	85
LaSOT: A High-quality Large-scale Single Object Tracking Benchmark	79
On the Arbitrary-Oriented Object Detection: Classification Based Approaches Revisited	77
Pixel-Wise Crowd Understanding via Synthetic Data	76
Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training	75
JÂA-Net: Joint Facial Action Unit Detection and Face Alignment Via Adaptive Attention	74
Unsupervised Deep Representation Learning for Real-Time Tracking	74
Curriculum Learning: A Survey	71
CLIP-Adapter: Better Vision-Language Models with Feature Adapters	68
Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis	63
A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains	63
ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond	59
Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild	59
Deformable Kernel Networks for Joint Image Filtering	58
Rain Rendering for Evaluating and Improving Robustness to Bad Weather	57
GhostNets on Heterogeneous Devices via Cheap Operations	56
Explainability of Deep Vision-Based Autonomous Driving Systems: Review and Challenges	55
Learning Adaptive Attribute-Driven Representation for Real-Time RGB-T Tracking	54
VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change	53
AutoScale: Learning to Scale for Crowd Counting	53
Structure-Measure: A New Way to Evaluate Foreground Maps	53
Adaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters	53
3D-FUTURE: 3D Furniture Shape with TextURE	49
Occluded Video Instance Segmentation: A Benchmark	48
Vis-MVSNet: Visibility-Aware Multi-view Stereo Network	47
An Exploration of Embodied Visual Exploration	47
Synthetic Humans for Action Recognition from Unseen Viewpoints	45
Countering Malicious DeepFakes: Survey, Battleground, and Horizon	45
Towards High Performance Human Keypoint Detection	44
A Comprehensive Benchmark Analysis of Single Image Deraining: Current Challenges and Future Perspectives	42
Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition Under Occlusion	42
The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation	41
A Survey on Long-Tailed Visual Recognition	41
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild	40
Train Sparsely, Generate Densely: Memory-Efficient Unsupervised Training of High-Resolution Temporal GAN	40
Scale-Aware Domain Adaptive Faster R-CNN	40
Bridging Composite and Real: Towards End-to-End Deep Image Matting	40
Context Autoencoder for Self-supervised Representation Learning	39
Multi-level Motion Attention for Human Motion Prediction	38
Twin Contrastive Learning for Online Clustering	37
Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning	37
Deep Nets: What have They Ever Done for Vision?	37
NormAttention-PSN: A High-frequency Region Enhanced Photometric Stereo Network with Normalized Attention	37
Quo Vadis, Skeleton Action Recognition?	36
Zero-Shot Object Detection: Joint Recognition and Localization of Novel Concepts	36
Viewpoint and Scale Consistency Reinforcement for UAV Vehicle Re-Identification	36
Semantic Edge Detection with Diverse Deep Supervision	35
Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization	35
SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds	34

Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild	32
Successive Graph Convolutional Network for Image De-raining	32
Low-light Image Enhancement via Breaking Down the Darkness	32
Learning to Reconstruct HDR Images from Events, with Applications to Depth and Flow Prediction	32
Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer	31
Manhattan Room Layout Reconstruction from a Single $$360^{\circ }$$ Image: A Comparative Study of State-of-the-Art Methods	30
Mimetics: Towards Understanding Human Actions Out of Context	30
3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation	30
Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks	29
Polysemy Deciphering Network for Robust Human–Object Interaction Detection	29
Benchmarking the Robustness of Semantic Segmentation Models with Respect to Common Corruptions	29
Compositional GAN: Learning Image-Conditional Binary Composition	28
MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation	28
Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction	27
LAMP-HQ: A Large-Scale Multi-pose High-Quality Database and Benchmark for NIR-VIS Face Recognition	27
Recursive Context Routing for Object Detection	27
Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization	26
SportsCap: Monocular 3D Human Motion Capture and Fine-Grained Understanding in Challenging Sports Videos	26
A Coarse-to-Fine Framework for Resource Efficient Video Recognition	26
Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior	26
Selective Wavelet Attention Learning for Single Image Deraining	26
Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild	25
Fine-Grained Instance-Level Sketch-Based Image Retrieval	25
RePCD-Net: Feature-Aware Recurrent Point Cloud Denoising Network	24
3D Semantic Scene Completion: A Survey	23
Feature Matching via Motion-Consistency Driven Probabilistic Graphical Model	23
Hadamard Matrix Guided Online Hashing	23
Parallel Single-Pixel Imaging: A General Method for Direct–Global Separation and 3D Shape Reconstruction Under Strong Global Illumination	23
Zero-Shot Learning on 3D Point Cloud Objects and Beyond	23
Unsupervised Domain Adaptation with Background Shift Mitigating for Person Re-Identification	23
Semantics-to-Signal Scalable Image Compression with Learned Revertible Representations	23
Dual Convolutional Neural Networks for Low-Level Vision	22
Learning Self-supervised Low-Rank Network for Single-Stage Weakly and Semi-supervised Semantic Segmentation	22
Talk2Nav: Long-Range Vision-and-Language Navigation with Dual Attention and Spatial Memory	22
Underwater Camera: Improving Visual Perception Via Adaptive Dark Pixel Prior and Color Correction	22
Multi-task Compositional Network for Visual Relationship Detection	22
SODA: Weakly Supervised Temporal Action Localization Based on Astute Background Response and Self-Distillation Learning	21
SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World	21
Dual-Attention-Guided Network for Ghost-Free High Dynamic Range Imaging	21
3D Object Detection for Autonomous Driving: A Comprehensive Survey	21
Spatial–Temporal Relation Reasoning for Action Prediction in Videos	20
Memory-Augmented Deep Unfolding Network for Guided Image Super-resolution	20
PhysFormer++: Facial Video-Based Physiological Measurement with SlowFast Temporal Difference Transformer	20
Joint Classification and Regression for Visual Tracking with Fully Convolutional Siamese Networks	20
On Measuring and Controlling the Spectral Bias of the Deep Image Prior	19
Context-Enhanced Representation Learning for Single Image Deraining	19
Learning Deep Patch representation for Probabilistic Graphical Model-Based Face Sketch Synthesis	19
Intra-Camera Supervised Person Re-Identification	19
OASIS: Only Adversarial Supervision for Semantic Image Synthesis	18
Adaptive Deep Disturbance-Disentangled Learning for Facial Expression Recognition	18
Multi-Modal 3D Object Detection in Autonomous Driving: A Survey	18
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling	18
A Shape Transformation-based Dataset Augmentation Framework for Pedestrian Detection	18
Enhanced 3D Human Pose Estimation from Videos by Using Attention-Based Neural Network with Dilated Convolutions	18
Dual-Constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior	18
REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets	18
RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning	18
Towards Balanced Learning for Instance Recognition	17
Delving Deeper into Anti-Aliasing in ConvNets	17
Vote-Based 3D Object Detection with Context Modeling and SOB-3DNMS	17
Incorporating Side Information by Adaptive Convolution	17
Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision	17
Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition	17
Learning Regression and Verification Networks for Robust Long-term Tracking	16
Learning to Detect Instance-Level Salient Objects Using Complementary Image Labels	16
Unsupervised Domain Adaptation in the Wild via Disentangling Representation Learning	16
Pyramid Attention Network for Image Restoration	16
Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection	16
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
Artificial Intelligence for Dunhuang Cultural Heritage Protection: The Project and the Dataset	15
Class-Difficulty Based Methods for Long-Tailed Visual Recognition	15
ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition	15
DeMoCap: Low-Cost Marker-Based Motion Capture	15
Delving into Inter-Image Invariance for Unsupervised Visual Representations	15
Residual Dual Scale Scene Text Spotting by Fusing Bottom-Up and Top-Down Processing	15
Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-Based Image Retrieval	15
SliderGAN: Synthesizing Expressive Face Images by Sliding 3D Blendshape Parameters	15
Pre-Training Without Natural Images	15

Label-Free Robustness Estimation of Object Detection CNNs for Autonomous Driving Applications	14
Revisiting Consistency Regularization for Semi-Supervised Learning	14
Attribute Prototype Network for Any-Shot Learning	14
Visual Object Tracking in First Person Vision	14
RoCGAN: Robust Conditional GAN	14
Face Image Reflection Removal	14
Beyond Covariance: SICE and Kernel Based Visual Feature Representation	14
EAN: Event Adaptive Network for Enhanced Action Recognition	14
Learning the Clustering of Longitudinal Shape Data Sets into a Mixture of Independent or Branching Trajectories	14
GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation	14
Guided Attention in CNNs for Occluded Pedestrian Detection and Re-identification	14
A Numerical Framework for Elastic Surface Matching, Comparison, and Interpolation	13
CDTD: A Large-Scale Cross-Domain Benchmark for Instance-Level Image-to-Image Translation and Domain Adaptive Object Detection	13
I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-Shaped Scene Text Detection	13
Sparse Black-Box Video Attack with Reinforcement Learning	13
Object Priors for Classifying and Localizing Unseen Actions	13
Multi-Object Tracking and Segmentation Via Neural Message Passing	13
A Benchmark and Evaluation of Non-Rigid Structure from Motion	13
AutoDet: Pyramid Network Architecture Search for Object Detection	13
Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors	12
Incremental Rotation Averaging	12
Distribution-Sensitive Information Retention for Accurate Binary Neural Network	12
Going Deeper than Tracking: A Survey of Computer-Vision Based Recognition of Animal Pain and Emotions	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
Multi-adversarial Faster-RCNN with Paradigm Teacher for Unrestricted Object Detection	12
Saliency Detection Inspired by Topological Perception Theory	12