IEEE Transactions on Pattern Analysis and Machine Intelligence

Article	Citations
OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields	2297
Deep High-Resolution Representation Learning for Visual Recognition	2045
Res2Net: A New Multi-Scale Backbone Architecture	1742
Image Segmentation Using Deep Learning: A Survey	1304
A Survey on Vision Transformer	1246
Deep Learning for 3D Point Clouds: A Survey	1024
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey	965
Deep Learning for Person Re-Identification: A Survey and Outlook	911
Deep Learning for Image Super-Resolution: A Survey	908
Event-Based Vision: A Survey	907
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild	838
U2Fusion: A Unified Unsupervised Image Fusion Network	829
Cascade R-CNN: High Quality Object Detection and Instance Segmentation	779
ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning	682
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer	585
Meta-Learning in Neural Networks: A Survey	528
Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection	528
Residual Dense Network for Image Restoration	528
Image Super-Resolution Via Iterative Refinement	507
A continual learning survey: Defying forgetting in classification tasks	504
Normalizing Flows: An Introduction and Review of Current Methods	465
Plug-and-Play Image Restoration With Deep Denoiser Prior	419
Recent Advances in Open Set Recognition: A Survey	410
Hierarchical Deep Click Feature Prediction for Fine-Grained Image Recognition	374
A Style-Based Generator Architecture for Generative Adversarial Networks	370

Salient Object Detection in the Deep Learning Era: An In-Depth Survey	323
Diffusion Models in Vision: A Survey	317
A Review of Domain Adaptation without Target Labels	310
Detection and Tracking Meet Drones Challenge	310
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks	304
Deep Multi-View Enhancement Hashing for Image Retrieval	303
Imbalance Problems in Object Detection: A Review	296
Multi-Task Learning for Dense Prediction Tasks: A Survey	294
Contextual Transformer Networks for Visual Recognition	292
Prior Guided Feature Enrichment Network for Few-Shot Segmentation	275
Domain Generalization: A Survey	272
Convolutional Networks with Dense Connectivity	263
Concealed Object Detection	255
NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization	252
Deep Audio-Visual Speech Recognition	252
High Speed and High Dynamic Range Video with an Event Camera	250
Dynamic Neural Networks: A Survey	249
YOLACT++ Better Real-Time Instance Segmentation	235
Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era	233
Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency	231
Low-Light Image and Video Enhancement Using Deep Learning: A Survey	225
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs	220
ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training	216
Deep Imbalanced Learning for Face Recognition and Attribute Prediction	215
Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks	214
Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation	206
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges	204
Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models	202
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals	201
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement	198
CCNet: Criss-Cross Attention for Semantic Segmentation	191
Revisiting Video Saliency Prediction in the Deep Learning Era	191
Human Action Recognition From Various Data Modalities: A Review	190
ArcFace: Additive Angular Margin Loss for Deep Face Recognition	186
Maximum Density Divergence for Domain Adaptation	182
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning	178
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	178
Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition	177
A Survey on Curriculum Learning	174
Class-Incremental Learning: Survey and Performance Evaluation on Image Classification	174
AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?	167
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D	166
Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion	163
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time	161
GAN Inversion: A Survey	158
SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing	157
Fine-Grained Image Analysis With Deep Learning: A Survey	153
Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification	151
Spatiotemporal Co-Attention Recurrent Neural Networks for Human-Skeleton Motion Prediction	150
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes	149

Video Anomaly Detection with Sparse Coding Inspired Deep Neural Networks	148
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	146
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction	145
Self-Correction for Human Parsing	141
Transfer Learning in Deep Reinforcement Learning: A Survey	141
The Emerging Trends of Multi-Label Learning	141
MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video	140
Single Image Deraining: From Model-Based to Data-Driven and Beyond	139
Learning Enriched Features for Fast Image Restoration and Enhancement	138
Graph U-Nets	137
Dynamical Hyperparameter Optimization via Deep Reinforcement Learning in Tracking	137
Coherence Constrained Graph LSTM for Group Activity Recognition	134
Weakly Supervised Object Localization and Detection: A Survey	134
Robust Multi-View Clustering With Incomplete Information	132
Densely Residual Laplacian Super-Resolution	131
Direction-Aware Spatial Context Features for Shadow Detection and Removal	131
MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion	130
Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods	127
Neural Image Compression for Gigapixel Histopathology Image Analysis	127
Robust Low-Rank Tensor Recovery with Rectification and Alignment	127
SpectralGPT: Spectral Remote Sensing Foundation Model	127
NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing	126
MTFH: A Matrix Tri-Factorization Hashing Framework for Efficient Cross-Modal Retrieval	126
From Show to Tell: A Survey on Deep Learning-Based Image Captioning	124
Multimodal Learning With Transformers: A Survey	124
A Comprehensive Survey of Scene Graphs: Generation and Application	123
Negation of the Quantum Mass Function for Multisource Quantum Information Fusion With its Application to Pattern Classification	123
Deep Long-Tailed Learning: A Survey	122
MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation	122
Graph Neural Networks with Convolutional ARMA Filters	122
CTNet: Context-Based Tandem Network for Semantic Segmentation	120
DeepFake Detection Based on Discrepancies Between Faces and Their Context	119
Learning Generalisable Omni-Scale Representations for Person Re-Identification	118
Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images	117
RGB-D SLAM in Dynamic Environments Using Point Correlations	114
Disentangling Light Fields for Super-Resolution and Disparity Estimation	114
Deep Convolutional Neural Network for Multi-Modal Image Restoration and Fusion	113
Person Re-Identification by Contour Sketch Under Moderate Clothing Change	112
UniFormer: Unifying Convolution and Self-Attention for Visual Recognition	111
Deep Residual Correction Network for Partial Domain Adaptation	110
A Novel Approach to Large-Scale Dynamically Weighted Directed Network Representation	109
ZeroNAS: Differentiable Generative Adversarial Networks Search for Zero-Shot Learning	109
Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition	108
Salient Object Detection via Integrity Learning	106
A Review of Generalized Zero-Shot Learning Methods	106
XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging	106
Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds	106
Explainability in Graph Neural Networks: A Taxonomic Survey	105
An End-to-End Learning Framework for Video Compression	105
Symbiotic Graph Neural Networks for 3D Skeleton-Based Human Action Recognition and Motion Prediction	105
Siamese Network for RGB-D Salient Object Detection and Beyond	104
Learning to Match Anchors for Visual Object Detection	104
A Review on Deep Learning Techniques for Video Prediction	103
Trusted Multi-View Classification With Dynamic Evidential Fusion	103
Towards Large-Scale Small Object Detection: Survey and Benchmarks	102
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation	100
Infinite Feature Selection: A Graph-based Feature Filtering Approach	98
Self-Supervised Learning of Graph Neural Networks: A Unified Review	98
Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms	98
A Lightweight Optical Flow CNN —Revisiting Data Fidelity and Regularization	97
SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild	97
Normalization Techniques in Training DNNs: Methodology, Analysis and Application	97
Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition	96
Deep ROC Analysis and AUC as Balanced Average Accuracy, for Improved Classifier Selection, Audit and Explanation	95
Segmenting Objects From Relational Visual Data	95
Enhanced Tensor RPCA and its Application	95
Saliency Prediction in the Deep Learning Era: Successes and Limitations	93
Tensor Low-Rank Representation for Data Recovery and Clustering	93
Structured Knowledge Distillation for Dense Prediction	93
Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL	92
P2T: Pyramid Pooling Transformer for Scene Understanding	92
Deep Gait Recognition: A Survey	91
Dual Encoding for Video Retrieval by Text	91
Distilled Siamese Networks for Visual Tracking	91
Physics-Based Generative Adversarial Models for Image Restoration and Beyond	91
Semi-Supervised Multi-View Deep Discriminant Representation Learning	91
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer	90
Graph Neural Networks in Network Neuroscience	89
Long-Term Visual Localization Revisited	89
Paying Attention to Video Object Pattern Understanding	89

Adversarial Reciprocal Points Learning for Open Set Recognition	89
High-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction	88
SensitiveNets: Learning Agnostic Representations with Application to Face Images	88
VOLO: Vision Outlooker for Visual Recognition	88
End-to-End Optimized Versatile Image Compression With Wavelet-Like Transform	88
TransFuser: Imitation With Transformer-Based Sensor Fusion for Autonomous Driving	88
Multiset Feature Learning for Highly Imbalanced Data Classification	86
Weakly Supervised Object Detection Using Proposal- and Semantic-Level Relationships	85
Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation	85
Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition	85
Neural Architecture Transfer	85
Deep Hough Transform for Semantic Line Detection	84
DeepMIH: Deep Invertible Network for Multiple Image Hiding	84
Restoring Vision in Adverse Weather Conditions With Patch-Based Denoising Diffusion Models	83
Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap	83
Parallax Attention for Unsupervised Stereo Correspondence Learning	82
Learning a Fixed-Length Fingerprint Representation	82
PoolNet+: Exploring the Potential of Pooling for Salient Object Detection	81
Fast and Robust Iterative Closest Point	81
Heterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain Adaptation	81
Augmentation Invariant and Instance Spreading Feature for Softmax Embedding	81
Line Graph Neural Networks for Link Prediction	79
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	79
Kernel-Based Density Map Generation for Dense Object Counting	79
A Bayesian Formulation of Coherent Point Drift	78
Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks	78
Context-Aware Visual Policy Network for Fine-Grained Image Captioning	78
Hyperbolic Deep Neural Networks: A Survey	77
Nonlinear Regression via Deep Negative Correlation Learning	77
Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy	76
Bayesian Temporal Factorization for Multidimensional Time Series Prediction	76
The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines	76
Higher-Order Explanations of Graph Neural Networks via Relevant Walks	76
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses	76
P-CNN: Part-Based Convolutional Neural Networks for Fine-Grained Visual Categorization	75
A Survey on Deep Learning Technique for Video Segmentation	74
Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting	74
Inferring Point Cloud Quality via Graph Similarity	73
Learning to Compose and Reason with Language Tree Structures for Visual Grounding	73
Bias in Cross-Entropy-Based Training of Deep Survival Networks	72
Deep Clustering: On the Link Between Discriminative Models and K-Means	72
Decentralized Federated Averaging	72
Affective Image Content Analysis: Two Decades Review and New Perspectives	72
Widar3.0: Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi	72
MobileSal: Extremely Efficient RGB-D Salient Object Detection	71
Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation	71
Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling	71
Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation	71
Learning Part-based Convolutional Features for Person Re-Identification	71
Re-thinking Co-Salient Object Detection	71
TransCenter: Transformers With Dense Representations for Multiple-Object Tracking	70
A Topological Loss Function for Deep-Learning Based Image Segmentation Using Persistent Homology	70
Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning	69
On Learning Disentangled Representations for Gait Recognition	69
Learning End-to-End Lossy Image Compression: A Benchmark	68
HGNN+: General Hypergraph Neural Networks	68
Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC	68
Deep Learning-based Multi-focus Image Fusion: A Survey and A Comparative Study	68
Towards Robust Discriminative Projections Learning via Non-Greedy -Norm MinMax	67
PVNet: Pixel-Wise Voting Network for 6DoF Object Pose Estimation	67
From Handcrafted to Deep Features for Pedestrian Detection: A Survey	67
Uncertainty Inspired RGB-D Saliency Detection	67
Hypergraph Learning: Methods and Practices	67
Real-World Image Denoising with Deep Boosting	67
Support Vector Machine Classifier via Soft-Margin Loss	66
Unsupervised Grouped Axial Data Modeling via Hierarchical Bayesian Nonparametric Models With Watson Distributions	66
Image De-Raining Transformer	65
Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation	65
Contrastive Learning with Stronger Augmentations	65
DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement	65
GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set	65
Learning to Model Relationships for Zero-Shot Video Classification	64
Base and Meta: A New Perspective on Few-Shot Segmentation	64
BDCN: Bi-Directional Cascade Network for Perceptual Edge Detection	64
AlignSeg: Feature-Aligned Segmentation Networks	63
Attention-Based Dropout Layer for Weakly Supervised Single Object Localization and Semantic Segmentation	63
A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video	63
Deep Back-ProjectiNetworks for Single Image Super-Resolution	63
Contrastive Adaptation Network for Single- and Multi-Source Domain Adaptation	62
HiGCIN: Hierarchical Graph-Based Cross Inference Network for Group Activity Recognition	62
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration	62
BlockQNN: Efficient Block-Wise Neural Network Architecture Generation	62
CoRRN: Cooperative Reflection Removal Network	61
Semantic Object Accuracy for Generative Text-to-Image Synthesis	61
Self-Distillation: Towards Efficient and Compact Neural Networks	61
What and How: Generalized Lifelong Spectral Clustering via Dual Memory	61
SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation	61
Towards a Complete 3D Morphable Model of the Human Head	61
Cascaded Parsing of Human-Object Interaction Recognition	60
Towards A Weakly Supervised Framework for 3D Point Cloud Object Detection and Annotation	60
A Fully Automated Method for 3D Individual Tooth Identification and Segmentation in Dental CBCT	60
NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size	60
PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-Step Point Moving Paths	60
MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network	59
End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network	59