IEEE Transactions on Pattern Analysis and Machine Intelligence

Papers
(The TQCC of IEEE Transactions on Pattern Analysis and Machine Intelligence is 21. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2021-05-01 to 2025-05-01.)
ArticleCitations
Learn to Predict Sets Using Feed-Forward Neural Networks2618
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus2079
Time-Resolved Far Infrared Light Transport Decomposition for Thermal Photometric Stereo1284
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data1225
Learning to Guide a Saturation-Based Theorem Prover1201
VATr++: Choose Your Words Wisely for Handwritten Text Generation1151
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification1131
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation1110
Modeling Noisy Annotations for Point-Wise Supervision1054
Face Forgery Detection by 3D Decomposition and Composition Search1050
Invariant Policy Learning: A Causal Perspective1022
Active Supervised Cross-Modal Retrieval820
Cover683
Editorial Board664
[Back inside cover]599
[Back cover - Table of contents, continued]590
Front Cover565
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach537
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images485
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models483
A Generative Model for Generic Light Field Reconstruction432
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications415
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing412
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference406
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting401
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems391
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks370
One-for-All: Towards Universal Domain Translation With a Single StyleGAN367
DVIS++: Improved Decoupled Framework for Universal Video Segmentation350
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation348
Deep Non-Rigid Structure From Motion With Missing Data342
Instance Shadow Detection with A Single-Stage Detector342
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation333
Physics-Informed Guided Disentanglement in Generative Networks331
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search323
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition318
Enhancing Representations through Heterogeneous Self-Supervised Learning317
Towards Accurate and Compact Architectures via Neural Architecture Transformer312
Inferring Point Cloud Quality via Graph Similarity308
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models302
Quadratic Matrix Factorization With Applications to Manifold Learning291
A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization287
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation286
Towards Unified Deep Image Deraining: A Survey and A New Benchmark283
Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures282
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification282
Transformer-Based Visual Segmentation: A Survey277
Affective Image Content Analysis: Two Decades Review and New Perspectives272
Are Graph Convolutional Networks With Random Weights Feasible?270
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution268
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains263
Prior Image Guided Snapshot Compressive Spectral Imaging254
Optimization-Based Post-Training Quantization With Bit-Split and Stitching251
Locating and Counting Heads in Crowds With a Depth Prior250
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks249
ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks244
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness230
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks229
Interactive NeRF Geometry Editing With Shape Priors224
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning222
Centerless Clustering215
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting213
Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting211
Graph Convolutional Module for Temporal Action Localization in Videos204
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion197
Simplicial Complex Neural Networks197
Structure-Preserving Image Super-Resolution194
Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes194
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method190
Face Generation and Editing With StyleGAN: A Survey188
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation186
Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching184
Deep Long-Tailed Learning: A Survey183
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration178
Unsupervised Domain Adaptation via Discriminative Manifold Propagation177
Multi-Task Head Pose Estimation in-the-Wild176
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation173
Fast Component Tree Computation for Images of Limited Levels172
Human-Centric Transformer for Domain Adaptive Action Recognition169
Cover 2168
Cover168
Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation167
Cover166
Cover166
Table of Contents166
IEEE Computer Society Has You Covered!165
Differentially Private Graph Neural Networks for Whole-Graph Classification164
Asymmetric Loss Functions for Noise-Tolerant Learning: Theory and Applications164
Orientational Distribution Learning with Hierarchical Spatial Attention for Open Set Recognition163
TPAMI Information for Authors161
Point Set Registration for 3D Range Scans Using Fuzzy Cluster-Based Metric and Efficient Global Optimization160
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks159
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning159
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation157
MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network155
BNET: Batch Normalization With Enhanced Linear Transformation155
Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond155
Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene154
VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision154
Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition150
AutoNovel: Automatically Discovering and Learning Novel Visual Categories148
Differential Viewpoints for Ground Terrain Material Recognition147
Compositional Scene Representation Learning via Reconstruction: A Survey146
GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector145
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets143
Fear-Neuro-Inspired Reinforcement Learning for Safe Autonomous Driving142
MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning141
A Variational EM Acceleration for Efficient Clustering at Very Large Scales136
Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification136
LMP-GAN: Out-Of-Distribution Detection For Non-Control Data Malware Attacks134
Rate-Distortion Theory in Coding for Machines and its Applications133
Interpretable Optimization-Inspired Unfolding Network for Low-Light Image Enhancement133
Enhancing Photorealism Enhancement132
Correcting Optical Aberration via Depth-Aware Point Spread Functions131
Self-Scalable Tanh (Stan): Multi-Scale Solutions for Physics-Informed Neural Networks131
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning131
Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification131
SPLiT: Single Portrait Lighting Estimation via a Tetrad of Face Intrinsics130
From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing129
Dynamic Self-Supervised Teacher-Student Network Learning126
Hypergraph-Based Multi-View Action Recognition Using Event Cameras126
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos125
Learning Graph Attentions via Replicator Dynamics122
GradMDM: Adversarial Attack on Dynamic Networks121
Revisiting Nonlocal Self-Similarity from Continuous Representation121
Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes for Pruning is Possible Without Retraining121
Discriminant Feature Extraction by Generalized Difference Subspace117
Human Interaction Understanding With Consistency-Aware Learning117
Out-of-Domain Generalization From a Single Source: An Uncertainty Quantification Approach117
Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation117
Inter-Intra Hypergraph Computation for Survival Prediction on Whole Slide Images115
Reduced-Rank Tensor-on-Tensor Regression and Tensor-Variate Analysis of Variance114
Adaptive Transfer Kernel Learning for Transfer Gaussian Process Regression114
Self-Supervised Multimodal Learning: A Survey112
Spatial-Temporal Transformer for Video Snapshot Compressive Imaging112
Domain Generalization: A Survey112
Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap111
On the Robustness of Average Losses for Partial-Label Learning111
Variational Data-Free Knowledge Distillation for Continual Learning111
Accurate and Efficient Stereo Matching via Attention Concatenation Volume111
Curriculum-Based Asymmetric Multi-Task Reinforcement Learning111
HiGCIN: Hierarchical Graph-Based Cross Inference Network for Group Activity Recognition110
Deep Gait Recognition: A Survey108
Learning From Partially Labeled Data for Multi-Organ and Tumor Segmentation108
Power Normalizations in Fine-Grained Image, Few-Shot Image and Graph Classification108
Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey107
Unbiased Scene Graph Generation via Two-Stage Causal Modeling107
Advances and Challenges in Meta-Learning: A Technical Review107
A Fully Automated Method for 3D Individual Tooth Identification and Segmentation in Dental CBCT106
P2T: Pyramid Pooling Transformer for Scene Understanding105
A New Brain Network Construction Paradigm for Brain Disorder via Diffusion-Based Graph Contrastive Learning105
PathNet: Path-Selective Point Cloud Denoising104
Random Permutation Set Reasoning103
Knowledge-Based Embodied Question Answering103
Learning to See Through With Events103
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses102
MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion102
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks101
Image-to-Image Translation With Disentangled Latent Vectors for Face Editing101
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking101
Deep Learning for Face Anti-Spoofing: A Survey101
On Positive-Unlabeled Classification from Corrupted Data in GANs98
ComputingEdge ad97
A Style-Based Generator Architecture for Generative Adversarial Networks97
Disentangled Representation Learning96
ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning96
RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging95
Adversarially Robust Neural Architectures95
Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset94
MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image Restoration94
Learning to Super-Resolve Blurry Images With Events94
DeepMesh: Differentiable Iso-Surface Extraction94
Joint Framework for Single Image Reconstruction and Super-Resolution With an Event Camera93
Quicker ADC : Unlocking the Hidden Potential of Product Quantization With SIMD93
Stimulative Training++: Go Beyond The Performance Limits of Residual Networks93
Deciphering the Feature Representation of Deep Neural Networks for High-Performance AI92
A Thorough Benchmark and a New Model for Light Field Saliency Detection91
JointFormer: A Unified Framework with Joint Modeling for Video Object Segmentation91
GhostingNet: A Novel Approach for Glass Surface Detection With Ghosting Cues91
SS-TBN: A Semi-Supervised Tri-Branch Network for COVID-19 Screening and Lesion Segmentation90
FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search90
Semi-Supervised Learning for FGVC With Out-of-Category Data90
Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation89
Conformal Prediction for Time Series89
$\mathcal {X}$-Metric: An N-Dimensional Information-Theoretic Framework for Groupwise Registration and Deep Combined Computing88
Learning With Constraint Learning: New Perspective, Solution Strategy and Various Applications87
Deep Learning on Object-Centric 3D Neural Fields86
Progressive Instance-Aware Feature Learning for Compositional Action Recognition85
Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization85
Adaptive Perspective Distillation for Semantic Segmentation84
Revealing the Dark Side of Non-Local Attention in Single Image Super-Resolution84
Homeomorphism Prior for False Positive and Negative Problem in Medical Image Dense Contrastive Representation Learning84
CycMuNet+: Cycle-Projected Mutual Learning for Spatial-Temporal Video Super-Resolution83
Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation83
Point Spatio-Temporal Transformer Networks for Point Cloud Video Modeling83
Support Vector Machine Classifier via Soft-Margin Loss83
Analysis of the Hands in Egocentric Vision: A Survey83
TE141K: Artistic Text Benchmark for Text Effect Transfer82
LCBM: A Multi-View Probabilistic Model for Multi-Label Classification82
[Back cover]82
Cover 381
Distributionally Location-Aware Transferable Adversarial Patches for Facial Images80
The Cluster Structure Function80
Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding80
Rolling Shutter Homography and its Applications79
Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses79
RGB-T Tracking With Template-Bridged Search Interaction and Target-Preserved Template Updating79
Editorial: Special Section on Egocentric Perception79
Multi-Modality Multi-Attribute Contrastive Pre-Training for Image Aesthetics Computing78
Reframing Neural Networks: Deep Structure in Overcomplete Representations78
AutoEval: Are Labels Always Necessary for Classifier Accuracy Evaluation?78
Scale Propagation Network for Generalizable Depth Completion77
An Energy-Based Prior for Generative Saliency77
The Bayesian Cut77
Noisy Label Learning With Provable Consistency for a Wider Family of Losses76
Optimizing Regularized Cholesky Score for Order-Based Learning of Bayesian Networks76
Unified Adversarial Patch for Visible-Infrared Cross-Modal Attacks in the Physical World76
STAR-FC: Structure-Aware Face Clustering on Ultra-Large-Scale Graphs76
Supervision by Denoising76
Reusable Architecture Growth for Continual Stereo Matching75
3D Visual Saliency: An Independent Perceptual Measure or A Derivative of 2D Image Saliency?75
CC4S: Encouraging Certainty and Consistency in Scribble-Supervised Semantic Segmentation75
Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images74
Heterogeneous Feature Re-Sampling for Balanced Pedestrian Attribute Recognition73
Low-shot Video Object Segmentation73
Generalized Task-Driven Medical Image Quality Enhancement With Gradient Promotion72
Reinforcing Generated Images via Meta-Learning for One-Shot Fine-Grained Visual Recognition72
Improving Machine Vision Using Human Perceptual Representations: The Case of Planar Reflection Symmetry for Object Classification72
Recurrent Neural Networks for Snapshot Compressive Imaging72
Test-time Training for Hyperspectral Image Super-resolution72
ONNXPruner: ONNX-Based General Model Pruning Adapter72
Pair Then Relation: Pair-Net for Panoptic Scene Graph Generation71
Semantic Object Accuracy for Generative Text-to-Image Synthesis71
luvHarris: A Practical Corner Detector for Event-Cameras71
Single Image Deraining: From Model-Based to Data-Driven and Beyond70
Dynamic Differential Image Circle Diameter Measurement Precision Assessment: Application to Burning Droplets70
TN-ZSTAD: Transferable Network for Zero-Shot Temporal Activity Detection70
Pixel Distillation: Cost-Flexible Distillation Across Image Sizes and Heterogeneous Networks70
Continual Unsupervised Generative Modeling70
IEEE Computer Society Has You Covered!69
On the Benefit of Optimal Transport for Curriculum Reinforcement Learning69
A Unified Framework for Event-Based Frame Interpolation With Ad-Hoc Deblurring in the Wild69
Cover 369
A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal69
Table of Contents69
Orientation Keypoints for 6D Human Pose Estimation69
Neural 3D Scene Reconstruction With Indoor Planar Priors68
Searching for Network Width With Bilaterally Coupled Network68
A Modular Neural Motion Retargeting System Decoupling Skeleton and Shape Perception68
FocalPose++: Focal Length and Object Pose Estimation via Render and Compare68
0.096323013305664