IEEE Transactions on Pattern Analysis and Machine Intelligence

Article	Citations
OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields	2220
Deep High-Resolution Representation Learning for Visual Recognition	1931
Res2Net: A New Multi-Scale Backbone Architecture	1674
Image Segmentation Using Deep Learning: A Survey	1249
A Survey on Vision Transformer	1130
Deep Learning for 3D Point Clouds: A Survey	985
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey	924
Deep Learning for Image Super-Resolution: A Survey	866
Deep Learning for Person Re-Identification: A Survey and Outlook	853
Event-Based Vision: A Survey	834
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding	805
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild	799
U2Fusion: A Unified Unsupervised Image Fusion Network	769
Cascade R-CNN: High Quality Object Detection and Instance Segmentation	742
ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning	634
Residual Dense Network for Image Restoration	506
Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection	502
Meta-Learning in Neural Networks: A Survey	501
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer	486
A continual learning survey: Defying forgetting in classification tasks	455
Normalizing Flows: An Introduction and Review of Current Methods	445
Image Super-Resolution Via Iterative Refinement	397
Recent Advances in Open Set Recognition: A Survey	394
Plug-and-Play Image Restoration With Deep Denoiser Prior	382
Hierarchical Deep Click Feature Prediction for Fine-Grained Image Recognition	373

A Style-Based Generator Architecture for Generative Adversarial Networks	344
Salient Object Detection in the Deep Learning Era: An In-Depth Survey	316
A Review of Domain Adaptation without Target Labels	303
Deep Multi-View Enhancement Hashing for Image Retrieval	298
Detection and Tracking Meet Drones Challenge	294
Imbalance Problems in Object Detection: A Review	293
The ApolloScape Open Dataset for Autonomous Driving and Its Application	292
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks	287
Multi-Task Learning for Dense Prediction Tasks: A Survey	275
Contextual Transformer Networks for Visual Recognition	269
Diffusion Models in Vision: A Survey	259
Convolutional Networks with Dense Connectivity	255
Prior Guided Feature Enrichment Network for Few-Shot Segmentation	247
NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization	244
Dynamic Neural Networks: A Survey	240
Deep Audio-Visual Speech Recognition	234
Domain Generalization: A Survey	231
High Speed and High Dynamic Range Video with an Event Camera	230
Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era	230
YOLACT++ Better Real-Time Instance Segmentation	227
Concealed Object Detection	226
Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency	215
Deep Imbalanced Learning for Face Recognition and Attribute Prediction	213
Low-Light Image and Video Enhancement Using Deep Learning: A Survey	209
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs	209
Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks	200
ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training	197
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals	193
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges	192
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement	191
CCNet: Criss-Cross Attention for Semantic Segmentation	187
Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation	187
Revisiting Video Saliency Prediction in the Deep Learning Era	186
Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models	186
Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos	179
Maximum Density Divergence for Domain Adaptation	178
Human Action Recognition From Various Data Modalities: A Review	176
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	173
ArcFace: Additive Angular Margin Loss for Deep Face Recognition	170
Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition	167
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning	163
Learning Depth with Convolutional Spatial Propagation Network	159
A Survey on Curriculum Learning	153
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding	152
SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing	151
A Comprehensive Analysis of Deep Regression	151
AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?	148
Video Anomaly Detection with Sparse Coding Inspired Deep Neural Networks	146
Spatiotemporal Co-Attention Recurrent Neural Networks for Human-Skeleton Motion Prediction	146
Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification	145

GAN Inversion: A Survey	144
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes	144
Class-Incremental Learning: Survey and Performance Evaluation on Image Classification	142
Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion	141
Confidence Propagation through CNNs for Guided Sparse Depth Regression	139
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time	139
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D	139
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	138
Fine-Grained Image Analysis With Deep Learning: A Survey	138
Single Image Deraining: From Model-Based to Data-Driven and Beyond	137
Dynamical Hyperparameter Optimization via Deep Reinforcement Learning in Tracking	136
MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video	136
Graph U-Nets	132
Coherence Constrained Graph LSTM for Group Activity Recognition	131
The Emerging Trends of Multi-Label Learning	130
Self-Correction for Human Parsing	128
Robust Low-Rank Tensor Recovery with Rectification and Alignment	127
Densely Residual Laplacian Super-Resolution	126
Weakly Supervised Object Localization and Detection: A Survey	125
MTFH: A Matrix Tri-Factorization Hashing Framework for Efficient Cross-Modal Retrieval	125
Direction-Aware Spatial Context Features for Shadow Detection and Removal	125
Neural Image Compression for Gigapixel Histopathology Image Analysis	125
Robust Multi-View Clustering With Incomplete Information	121
Negation of the Quantum Mass Function for Multisource Quantum Information Fusion With its Application to Pattern Classification	121
NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing	121
MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion	120
Learning Enriched Features for Fast Image Restoration and Enhancement	120
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction	120
Transfer Learning in Deep Reinforcement Learning: A Survey	118
A Comprehensive Survey of Scene Graphs: Generation and Application	117
Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods	117
Graph Neural Networks with Convolutional ARMA Filters	117
Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images	116
Learning Generalisable Omni-Scale Representations for Person Re-Identification	115
From Show to Tell: A Survey on Deep Learning-Based Image Captioning	115
MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation	115
DeepFake Detection Based on Discrepancies Between Faces and Their Context	114
CTNet: Context-Based Tandem Network for Semantic Segmentation	111
RGB-D SLAM in Dynamic Environments Using Point Correlations	111
Disentangling Light Fields for Super-Resolution and Disparity Estimation	110
ZeroNAS: Differentiable Generative Adversarial Networks Search for Zero-Shot Learning	109
A Novel Approach to Large-Scale Dynamically Weighted Directed Network Representation	109
Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition	108
Person Re-Identification by Contour Sketch Under Moderate Clothing Change	107
Deep Residual Correction Network for Partial Domain Adaptation	107
Deep Convolutional Neural Network for Multi-Modal Image Restoration and Fusion	106
Learning to Match Anchors for Visual Object Detection	104
Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds	103
Symbiotic Graph Neural Networks for 3D Skeleton-Based Human Action Recognition and Motion Prediction	103
Siamese Network for RGB-D Salient Object Detection and Beyond	102
An End-to-End Learning Framework for Video Compression	102
XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging	102
UniFormer: Unifying Convolution and Self-Attention for Visual Recognition	101
Salient Object Detection via Integrity Learning	101
Deep Long-Tailed Learning: A Survey	100
Explainability in Graph Neural Networks: A Taxonomic Survey	100
Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle	98
SpectralGPT: Spectral Remote Sensing Foundation Model	98
Multimodal Learning With Transformers: A Survey	98
A Review on Deep Learning Techniques for Video Prediction	98
Trusted Multi-View Classification With Dynamic Evidential Fusion	97
A Review of Generalized Zero-Shot Learning Methods	97
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation	97
Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms	95
SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild	93
Segmenting Objects From Relational Visual Data	93
Enhanced Tensor RPCA and its Application	93
Self-Supervised Learning of Graph Neural Networks: A Unified Review	92
Infinite Feature Selection: A Graph-based Feature Filtering Approach	92
Structured Knowledge Distillation for Dense Prediction	92
Tensor Low-Rank Representation for Data Recovery and Clustering	92
Dual Encoding for Video Retrieval by Text	91
Saliency Prediction in the Deep Learning Era: Successes and Limitations	91
Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition	91
Deep ROC Analysis and AUC as Balanced Average Accuracy, for Improved Classifier Selection, Audit and Explanation	91
Semi-Supervised Multi-View Deep Discriminant Representation Learning	90
Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL	90
Paying Attention to Video Object Pattern Understanding	89
A Lightweight Optical Flow CNN —Revisiting Data Fidelity and Regularization	88
Distilled Siamese Networks for Visual Tracking	88

Physics-Based Generative Adversarial Models for Image Restoration and Beyond	87
P2T: Pyramid Pooling Transformer for Scene Understanding	87
High-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction	87
Deep Gait Recognition: A Survey	86
Multiset Feature Learning for Highly Imbalanced Data Classification	86
Towards Large-Scale Small Object Detection: Survey and Benchmarks	85
SensitiveNets: Learning Agnostic Representations with Application to Face Images	85
End-to-End Optimized Versatile Image Compression With Wavelet-Like Transform	85
Graph Neural Networks in Network Neuroscience	85
Normalization Techniques in Training DNNs: Methodology, Analysis and Application	83
Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation	83
Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition	83
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer	82
Deep Hough Transform for Semantic Line Detection	82
Long-Term Visual Localization Revisited	82
Weakly Supervised Object Detection Using Proposal- and Semantic-Level Relationships	82
Augmentation Invariant and Instance Spreading Feature for Softmax Embedding	81
VOLO: Vision Outlooker for Visual Recognition	81
Neural Architecture Transfer	81
Adversarial Reciprocal Points Learning for Open Set Recognition	81
Learning a Fixed-Length Fingerprint Representation	79
DeepMIH: Deep Invertible Network for Multiple Image Hiding	79
Heterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain Adaptation	78
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	78
TransFuser: Imitation With Transformer-Based Sensor Fusion for Autonomous Driving	78
Fast and Robust Iterative Closest Point	77
Parallax Attention for Unsupervised Stereo Correspondence Learning	77
Context-Aware Visual Policy Network for Fine-Grained Image Captioning	77
A Bayesian Formulation of Coherent Point Drift	77
Line Graph Neural Networks for Link Prediction	76
Nonlinear Regression via Deep Negative Correlation Learning	76
PoolNet+: Exploring the Potential of Pooling for Salient Object Detection	76
Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap	76
P-CNN: Part-Based Convolutional Neural Networks for Fine-Grained Visual Categorization	74
Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy	73
Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks	73
Kernel-Based Density Map Generation for Dense Object Counting	73
Hyperbolic Deep Neural Networks: A Survey	73
Bayesian Temporal Factorization for Multidimensional Time Series Prediction	72
The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines	72
Multi-Source Causal Feature Selection	72
Higher-Order Explanations of Graph Neural Networks via Relevant Walks	71
Learning Part-based Convolutional Features for Person Re-Identification	71
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses	70
Re-thinking Co-Salient Object Detection	70
Deep Clustering: On the Link Between Discriminative Models and K-Means	70
Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation	70
MobileSal: Extremely Efficient RGB-D Salient Object Detection	69
Inferring Point Cloud Quality via Graph Similarity	69
Widar3.0: Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi	68
A Survey on Deep Learning Technique for Video Segmentation	67
Decentralized Federated Averaging	67
Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting	66
Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling	66
Learning to Compose and Reason with Language Tree Structures for Visual Grounding	66
Bias in Cross-Entropy-Based Training of Deep Survival Networks	66
Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning	66
Uncertainty Inspired RGB-D Saliency Detection	66
Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation	66
Towards Robust Discriminative Projections Learning via Non-Greedy -Norm MinMax	65
PVNet: Pixel-Wise Voting Network for 6DoF Object Pose Estimation	65
On Learning Disentangled Representations for Gait Recognition	65
Learning End-to-End Lossy Image Compression: A Benchmark	65
Deep Learning-based Multi-focus Image Fusion: A Survey and A Comparative Study	65
A Topological Loss Function for Deep-Learning Based Image Segmentation Using Persistent Homology	65
Unsupervised Grouped Axial Data Modeling via Hierarchical Bayesian Nonparametric Models With Watson Distributions	65
Restoring Vision in Adverse Weather Conditions With Patch-Based Denoising Diffusion Models	64
Support Vector Machine Classifier via Soft-Margin Loss	64
Hypergraph Learning: Methods and Practices	63
From Handcrafted to Deep Features for Pedestrian Detection: A Survey	63
BDCN: Bi-Directional Cascade Network for Perceptual Edge Detection	63
TransCenter: Transformers With Dense Representations for Multiple-Object Tracking	63
Contrastive Learning with Stronger Augmentations	63
Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC	62
AlignSeg: Feature-Aligned Segmentation Networks	62
GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set	62
Attention-Based Dropout Layer for Weakly Supervised Single Object Localization and Semantic Segmentation	61
Real-World Image Denoising with Deep Boosting	61
HiGCIN: Hierarchical Graph-Based Cross Inference Network for Group Activity Recognition	61
Learning to Model Relationships for Zero-Shot Video Classification	61
BlockQNN: Efficient Block-Wise Neural Network Architecture Generation	61
Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation	61
The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers	61
A Fully Automated Method for 3D Individual Tooth Identification and Segmentation in Dental CBCT	61
Affective Image Content Analysis: Two Decades Review and New Perspectives	61
HGNN+: General Hypergraph Neural Networks	60
Cascaded Parsing of Human-Object Interaction Recognition	60
Deep Back-ProjectiNetworks for Single Image Super-Resolution	60
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration	59
MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network	59
DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement	59
Towards a Complete 3D Morphable Model of the Human Head	59
Semantic Object Accuracy for Generative Text-to-Image Synthesis	58
What and How: Generalized Lifelong Spectral Clustering via Dual Memory	58
Self-Distillation: Towards Efficient and Compact Neural Networks	58