IEEE Transactions on Pattern Analysis and Machine Intelligence

Article	Citations
Learn to Predict Sets Using Feed-Forward Neural Networks	2777
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus	2327
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification	1344
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation	1312
Modeling Noisy Annotations for Point-Wise Supervision	1268
Invariant Policy Learning: A Causal Perspective	1218
Cover	1195
Editorial Board	1171
[Back cover - Table of contents, continued]	1154
Front Cover	870
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	775
A Generative Model for Generic Light Field Reconstruction	739
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing	627
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference	627
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	618
Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting	560
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data	539
Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching	519
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	473
Deep Non-Rigid Structure From Motion With Missing Data	449
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	444
Towards Unified Deep Image Deraining: A Survey and a New Benchmark	429
Enhancing Representations Through Heterogeneous Self-Supervised Learning	417
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	405
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	399

ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting	393
Learning to Guide a Saturation-Based Theorem Prover	383
Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes	378
Centerless Clustering	367
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning	363
A Clustering Validity Index with Multi-Granularity Fusion for Multiple Fuzzy Clustering Algorithms	357
Structure-Preserving Image Super-Resolution	353
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search	350
Quadratic Matrix Factorization With Applications to Manifold Learning	341
A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization	341
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks	338
Interactive NeRF Geometry Editing With Shape Priors	331
Towards Accurate and Compact Architectures via Neural Architecture Transformer	321
ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks	321
Graph Convolutional Module for Temporal Action Localization in Videos	310
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	301
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	296
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models	294
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach	290
Instance Shadow Detection with A Single-Stage Detector	283
Physics-Informed Guided Disentanglement in Generative Networks	283
VATr++: Choose Your Words Wisely for Handwritten Text Generation	281
Multi-Task Head Pose Estimation in-the-Wild	270
Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures	270
Locating and Counting Heads in Crowds With a Depth Prior	265
Simplicial Complex Neural Networks	264
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	257
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	255
On the Trade-off between Flatness and Optimization in Distributed Learning	249
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	244
Are Graph Convolutional Networks With Random Weights Feasible?	235
Active Supervised Cross-Modal Retrieval	234
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification	223
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	223
Transformer-Based Visual Segmentation: A Survey	222
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	219
Prior Image Guided Snapshot Compressive Spectral Imaging	217
Affective Image Content Analysis: Two Decades Review and New Perspectives	216
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition	215
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	204
Deep Long-Tailed Learning: A Survey	204
Face Forgery Detection by 3D Decomposition and Composition Search	203
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration	203
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	200
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	197
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	197
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks	186
Inferring Point Cloud Quality via Graph Similarity	185
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	185
Face Generation and Editing With StyleGAN: A Survey	182

Fast Component Tree Computation for Images of Limited Levels	181
Unsupervised Domain Adaptation via Discriminative Manifold Propagation	181
Cover	179
Human-Centric Transformer for Domain Adaptive Action Recognition	179
Cover 2	178
Cover	177
Cover	176
Table of Contents	175
IEEE Computer Society Has You Covered!	175
TPAMI Information for Authors	174
Point Set Registration for 3D Range Scans Using Fuzzy Cluster-Based Metric and Efficient Global Optimization	171
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning	171
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets	169
A Variational EM Acceleration for Efficient Clustering at Very Large Scales	169
Compositional Scene Representation Learning via Reconstruction: A Survey	167
Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey	165
MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network	164
Image Lens Flare Removal Using Adversarial Curve Learning	163
On the Robustness of Average Losses for Partial-Label Learning	161
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks	159
Learning to See Through With Events	158
PathNet: Path-Selective Point Cloud Denoising	157
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation	157
Out-of-Domain Generalization From a Single Source: An Uncertainty Quantification Approach	157
Self-Supervised Multimodal Learning: A Survey	156
LMP-GAN: Out-of-Distribution Detection for Non-Control Data Malware Attacks	156
Image-to-Image Translation With Disentangled Latent Vectors for Face Editing	155
Interpretable Optimization-Inspired Unfolding Network for Low-Light Image Enhancement	151
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation	149
Rate-Distortion Theory in Coding for Machines and Its Applications	149
Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation	147
Discriminant Feature Extraction by Generalized Difference Subspace	146
Knowledge-Based Embodied Question Answering	144
Universal Image Segmentation with Efficiency	140
Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification	139
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning	138
SPLiT: Single Portrait Lighting Estimation via a Tetrad of Face Intrinsics	134
Dynamic Self-Supervised Teacher-Student Network Learning	133
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos	132
Learning Graph Attentions via Replicator Dynamics	132
GradMDM: Adversarial Attack on Dynamic Networks	130
Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes for Pruning is Possible Without Retraining	130
Human Interaction Understanding With Consistency-Aware Learning	129
Orientational Distribution Learning with Hierarchical Spatial Attention for Open Set Recognition	127
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks	127
Differential Viewpoints for Ground Terrain Material Recognition	126
Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation	125
Asymmetric Loss Functions for Noise-Tolerant Learning: Theory and Applications	123
Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification	123
Unbiased Scene Graph Generation via Two-Stage Causal Modeling	123
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration	122
Reduced-Rank Tensor-on-Tensor Regression and Tensor-Variate Analysis of Variance	121
On Positive-Unlabeled Classification from Corrupted Data in GANs	119
Enhancing Photorealism Enhancement	118
Adaptive Transfer Kernel Learning for Transfer Gaussian Process Regression	118
Self-Scalable Tanh (Stan): Multi-Scale Solutions for Physics-Informed Neural Networks	117
AutoNovel: Automatically Discovering and Learning Novel Visual Categories	117
Learning From Partially Labeled Data for Multi-Organ and Tumor Segmentation	117
Revisiting Nonlocal Self-Similarity from Continuous Representation	116
Correcting Optical Aberration via Depth-Aware Point Spread Functions	115
Accurate and Efficient Stereo Matching via Attention Concatenation Volume	115
HiGCIN: Hierarchical Graph-Based Cross Inference Network for Group Activity Recognition	115
Random Permutation Set Reasoning	114
Domain Generalization: A Survey	114
Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition	113
Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond	113
Hypergraph-Based Multi-View Action Recognition Using Event Cameras	113
Curriculum-Based Asymmetric Multi-Task Reinforcement Learning	113
Differentially Private Graph Neural Networks for Whole-Graph Classification	111
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking	110
VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision	107
BNET: Batch Normalization With Enhanced Linear Transformation	107
Fear-Neuro-Inspired Reinforcement Learning for Safe Autonomous Driving	106
P2T: Pyramid Pooling Transformer for Scene Understanding	106
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses	106
Spatial-Temporal Transformer for Video Snapshot Compressive Imaging	105
Power Normalizations in Fine-Grained Image, Few-Shot Image and Graph Classification	105
A Fully Automated Method for 3D Individual Tooth Identification and Segmentation in Dental CBCT	103
MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion	103
Inter-Intra Hypergraph Computation for Survival Prediction on Whole Slide Images	102

MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning	100
A New Brain Network Construction Paradigm for Brain Disorder via Diffusion-Based Graph Contrastive Learning	100
Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap	100
Deep Learning for Face Anti-Spoofing: A Survey	99
Variational Data-Free Knowledge Distillation for Continual Learning	99
Deep Gait Recognition: A Survey	99
GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector	99
From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing	99
ComputingEdge ad	98
Advances and Challenges in Meta-Learning: A Technical Review	98
A Style-Based Generator Architecture for Generative Adversarial Networks	98
ONNXPruner: ONNX-Based General Model Pruning Adapter	97
JointFormer: A Unified Framework With Joint Modeling for Video Object Segmentation	97
Support Vector Machine Classifier via Soft-Margin Loss	97
Human as Points: Explicit Point-Based 3D Human Reconstruction From Single-View RGB Images	97
LCBM: A Multi-View Probabilistic Model for Multi-Label Classification	97
luvHarris: A Practical Corner Detector for Event-Cameras	97
Low-Shot Video Object Segmentation	95
Multi-Modality Multi-Attribute Contrastive Pre-Training for Image Aesthetics Computing	94
RGB-T Tracking With Template-Bridged Search Interaction and Target-Preserved Template Updating	93
Dynamic Differential Image Circle Diameter Measurement Precision Assessment: Application to Burning Droplets	93
Learning With Constraint Learning: New Perspective, Solution Strategy and Various Applications	93
DeepMesh: Differentiable Iso-Surface Extraction	93
Stimulative Training++: Go Beyond The Performance Limits of Residual Networks	92
Semi-Supervised Learning for FGVC With Out-of-Category Data	92
ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning	92
FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search	92
TN-ZSTAD: Transferable Network for Zero-Shot Temporal Activity Detection	91
Homeomorphism Prior for False Positive and Negative Problem in Medical Image Dense Contrastive Representation Learning	91
Relationship Quantification of Image Degradations	91
Continual Unsupervised Generative Modeling	91
Joint Framework for Single Image Reconstruction and Super-Resolution With an Event Camera	91
Improving Machine Vision Using Human Perceptual Representations: The Case of Planar Reflection Symmetry for Object Classification	91
Cover 3	89
Distributionally Location-Aware Transferable Adversarial Patches for Facial Images	89
The Cluster Structure Function	87
Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding	87
Editorial: Special Section on Egocentric Perception	87
An Energy-Based Prior for Generative Saliency	86
Reusable Architecture Growth for Continual Stereo Matching	86
CC4S: Encouraging Certainty and Consistency in Scribble-Supervised Semantic Segmentation	86
Scale Propagation Network for Generalizable Depth Completion	86
Test-time Training for Hyperspectral Image Super-resolution	85
3D Visual Saliency: An Independent Perceptual Measure or A Derivative of 2D Image Saliency?	85
Generalized Task-Driven Medical Image Quality Enhancement With Gradient Promotion	85
Supervision by Denoising	85
Heterogeneous Feature Re-Sampling for Balanced Pedestrian Attribute Recognition	85
Deep Learning on Object-Centric 3D Neural Fields	84
TE141K: Artistic Text Benchmark for Text Effect Transfer	84
Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset	84
A Thorough Benchmark and a New Model for Light Field Saliency Detection	84
On the Universal Approximation Properties of Deep Neural Networks Using MAM Neurons	84
GhostingNet: A Novel Approach for Glass Surface Detection With Ghosting Cues	83
FreeFusion: Infrared and Visible Image Fusion via Cross Reconstruction Learning	83
Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation	83
MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video	83
Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization	82
Rolling Shutter Homography and its Applications	82
CycMuNet+: Cycle-Projected Mutual Learning for Spatial-Temporal Video Super-Resolution	80
Compositional Physical Reasoning of Objects and Events from Videos	80
Learning to Super-Resolve Blurry Images With Events	80
Reframing Neural Networks: Deep Structure in Overcomplete Representations	80
Reinforcing Generated Images via Meta-Learning for One-Shot Fine-Grained Visual Recognition	79
RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging	79
Recurrent Neural Networks for Snapshot Compressive Imaging	79
AutoEval: Are Labels Always Necessary for Classifier Accuracy Evaluation?	79
Noisy Label Learning With Provable Consistency for a Wider Family of Losses	79
Pair Then Relation: Pair-Net for Panoptic Scene Graph Generation	79
$\mathcal {X}$-Metric: An N-Dimensional Information-Theoretic Framework for Groupwise Registration and Deep Combined Computing	79
S $^{2}$ O: Enhancing Adversarial Training with Second-Order Statistics of Weights	78
Adversarially Robust Neural Architectures	78
Cascaded Dynamic Memory Refinement and Semantic Alignment for Exo-to-Ego Cross-View Video Generation	78
SS-TBN: A Semi-Supervised Tri-Branch Network for COVID-19 Screening and Lesion Segmentation	78
Disentangled Representation Learning	77
Deciphering the Feature Representation of Deep Neural Networks for High-Performance AI	77
Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses	76
Any Fashion Attribute Editing: Dataset and Pretrained Models	75
Progressive Instance-Aware Feature Learning for Compositional Action Recognition	75
Conformal Prediction for Time Series	75
Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation	74
The Bayesian Cut	74
STAR-FC: Structure-Aware Face Clustering on Ultra-Large-Scale Graphs	74
Analysis of the Hands in Egocentric Vision: A Survey	74
Revealing the Dark Side of Non-Local Attention in Single Image Super-Resolution	74
Adaptive Perspective Distillation for Semantic Segmentation	73
Point Spatio-Temporal Transformer Networks for Point Cloud Video Modeling	73
MB-TaylorFormer V2: Improved Multi-Branch Linear Transformer Expanded by Taylor Formula for Image Restoration	73
Optimizing Regularized Cholesky Score for Order-Based Learning of Bayesian Networks	73
Semantic Object Accuracy for Generative Text-to-Image Synthesis	73
Unified Adversarial Patch for Visible-Infrared Cross-Modal Attacks in the Physical World	73
IEEE Computer Society Has You Covered!	72
Pixel Distillation: Cost-Flexible Distillation Across Image Sizes and Heterogeneous Networks	72
Cover 3	72
Single Image Deraining: From Model-Based to Data-Driven and Beyond	72
Table of Contents	72