IEEE Transactions on Pattern Analysis and Machine Intelligence

Article	Citations
Front Cover	3719
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	1923
On the Trade-Off Between Flatness and Optimization in Distributed Learning	1676
Learning to Guide a Saturation-Based Theorem Prover	1504
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning	935
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search	889
Interactive NeRF Geometry Editing With Shape Priors	757
Self-Supervised Skeleton Representation Learning Via Actionlet Contrast and Reconstruct	695
Editorial: Introduction to the Special Section on Best of CVPR'2022	695
BiBBDM: Bidirectional Image Translation With Brownian Bridge Diffusion Models	667
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models	661
A Clustering Validity Index With Multi-Granularity Fusion for Multiple Fuzzy Clustering Algorithms	655
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach	652
Video Demoireing Using Focused-Defocused Dual-Camera System	615
Invariant Policy Learning: A Causal Perspective	596
A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization	588
Towards Accurate and Compact Architectures via Neural Architecture Transformer	581
Seeing Through Satellite Images at Street Views	564
Next Bit Prediction: A Unified Lossless and Lossy Point Cloud Geometry Compression Framework	539
LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting	536
Modeling Noisy Annotations for Point-Wise Supervision	526
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	523
Test-Time Correction: An Online 3D Detection System via Visual Prompting	516
Simplicial Complex Neural Networks	488
Like Human Rethinking: Contour Transformer AutoRegression for Referring Remote Sensing Interpretation	486

Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures	472
Rethinking Rotation-Invariant Recognition of Fine-Grained Shapes From the Perspective of Contour Points	453
SNI-SLAM++: Tightly-Coupled Semantic Neural Implicit SLAM	443
Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective	436
MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning	435
A Personalized and Privacy-Preserving Federated Transformer Framework for Multilingual Sentiment Analysis	431
Quadratic Matrix Factorization With Applications to Manifold Learning	428
Graph Convolutional Module for Temporal Action Localization in Videos	421
Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting	405
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing	402
Learn to Predict Sets Using Feed-Forward Neural Networks	402
Physics-Informed Guided Disentanglement in Generative Networks	396
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	375
Prior Image Guided Snapshot Compressive Spectral Imaging	371
Inferring Point Cloud Quality via Graph Similarity	370
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	370
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	360
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference	353
AIRPNet: Adaptive Image Restoration With Privacy Protection in Steganographic Domain	353
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification	352
Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers	351
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data	338
Face Forgery Detection by 3D Decomposition and Composition Search	324
SCGT: Towards Scalable and Comprehensive Graph Transformer	304
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration	303
Face Generation and Editing With StyleGAN: A Survey	299
Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes	295
VATr++: Choose Your Words Wisely for Handwritten Text Generation	293
Are Graph Convolutional Networks With Random Weights Feasible?	293
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	292
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	292
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	283
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification	281
Towards Unified Deep Image Deraining: A Survey and a New Benchmark	280
Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations	276
Reliable and Compact Graph Fine-Tuning Via Graph Sparse Prompting	275
Transformer-Based Visual Segmentation: A Survey	269
Structure-Preserving Image Super-Resolution	268
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting	264
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	259
Enhancing Representations Through Heterogeneous Self-Supervised Learning	259
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	247
Centerless Clustering	247
Affective Image Content Analysis: Two Decades Review and New Perspectives	238
Active Supervised Cross-Modal Retrieval	234
Locating and Counting Heads in Crowds With a Depth Prior	231
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition	229
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation	227
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	227
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	227

Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching	226
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus	224
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	224
Deep Long-Tailed Learning: A Survey	220
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	220
Event-Based Photometric Bundle Adjustment	219
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	217
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks	213
Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Models	212
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	212
Cover 2	209
BNET: Batch Normalization With Enhanced Linear Transformation	208
Temporal Feature Matters: A Framework for Diffusion Model Quantization	206
Unbiased Scene Graph Generation via Two-Stage Causal Modeling	203
GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector	200
Rate-Distortion Theory in Coding for Machines and Its Applications	199
On the Robustness of Average Losses for Partial-Label Learning	199
A Unified Experience Replay Framework for Spiking Deep Reinforcement Learning	198
MESA: Effective Matching Redundancy Reduction by Semantic Area Segmentation	197
Universal Image Segmentation With Efficiency	188
Supervised Small-baseline and Large-baseline Homography Learning with Diffusion-based Data Generation	188
Correcting Optical Aberration via Depth-Aware Point Spread Functions	184
To Fold or Not to Fold: Graph Regularized Tensor Train for Visual Data Completion	184
Image-to-Image Translation With Disentangled Latent Vectors for Face Editing	184
Adaptive Transfer Kernel Learning for Transfer Gaussian Process Regression	180
Self-Scalable Tanh (Stan): Multi-Scale Solutions for Physics-Informed Neural Networks	176
Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation	176
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation	175
Human Interaction Understanding With Consistency-Aware Learning	173
GradMDM: Adversarial Attack on Dynamic Networks	173
Deep Orientational Representation Learning for Ordinal Regression	172
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning	170
Graph-Oriented Instruction Tuning of Large Language Models for Generic Graph Mining	170
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation	169
Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification	168
Understanding the Effects of Projectors in Knowledge Distillation	167
Compositional Scene Representation Learning via Reconstruction: A Survey	166
Hypergraph-Based Multi-View Action Recognition Using Event Cameras	166
Learning Graph Attentions via Replicator Dynamics	166
Inter-Intra Hypergraph Computation for Survival Prediction on Whole Slide Images	166
Discriminant Feature Extraction by Generalized Difference Subspace	165
SPLiT: Single Portrait Lighting Estimation via a Tetrad of Face Intrinsics	165
Learning to See Through With Events	163
Thermal3D-GS: Physics-induced 3D Gaussians for Thermal Infrared Novel-view Synthesis with a Large-Scale Dataset	163
LMP-GAN: Out-of-Distribution Detection for Non-Control Data Malware Attacks	161
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning	160
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks	160
Controllable Generation With Text-to-Image Diffusion Models: A Survey	159
VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision	158
Image Lens Flare Removal Using Adversarial Curve Learning	158
Continuous Review and Timely Correction: Enhancing the Resistance to Noisy Labels via Self-Not-True and Class-Wise Distillation	158
Revisiting Nonlocal Self-Similarity from Continuous Representation	157
AutoNovel: Automatically Discovering and Learning Novel Visual Categories	157
Interpretable Optimization-Inspired Unfolding Network for Low-Light Image Enhancement	156
A New Brain Network Construction Paradigm for Brain Disorder via Diffusion-Based Graph Contrastive Learning	156
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos	153
Variational Data-Free Knowledge Distillation for Continual Learning	151
Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization	150
SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration	149
Curriculum-Based Asymmetric Multi-Task Reinforcement Learning	148
Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition	148
EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning	147
Deep Learning-Based Point Cloud Compression: An In-Depth Survey and Benchmark	146
A Unified Decision Rule for Generalized Out-of-Distribution Detection	145
Learning From Partially Labeled Data for Multi-Organ and Tumor Segmentation	145
Physics-Informed Matrix Factorization Operator	143
Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights	142
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration	142
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets	138
Learning Efficient Meshflow and Optical Flow From Event Cameras	137
On Positive-Unlabeled Classification From Corrupted Data in GANs	137
A Variational EM Acceleration for Efficient Clustering at Very Large Scales	137
Privacy Preserving Decentralized Learning with Positive-Incentive Noise	135
InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis With Semantic Graph Prior	135
M$^{3}$3D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-Level Information Extraction	134
Asymmetric Loss Functions for Noise-Tolerant Learning: Theory and Applications	134
From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing	133
Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap	132
Human-Centric Transformer for Domain Adaptive Action Recognition	132
Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation	132

Out-of-Domain Generalization From a Single Source: An Uncertainty Quantification Approach	132
A Fully Automated Method for 3D Individual Tooth Identification and Segmentation in Dental CBCT	132
Enhancing Photorealism Enhancement	129
Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes for Pruning is Possible Without Retraining	128
Reduced-Rank Tensor-on-Tensor Regression and Tensor-Variate Analysis of Variance	128
HiGCIN: Hierarchical Graph-Based Cross Inference Network for Group Activity Recognition	128
Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification	127
Differentially Private Graph Neural Networks for Whole-Graph Classification	126
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses	126
Fear-Neuro-Inspired Reinforcement Learning for Safe Autonomous Driving	126
PathNet: Path-Selective Point Cloud Denoising	125
Random Permutation Set Reasoning	125
Accurate and Efficient Stereo Matching via Attention Concatenation Volume	124
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking	123
Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond	122
Deep Gait Recognition: A Survey	122
Mining Association Patterns From Neighborhood Insight	122
Advances and Challenges in Meta-Learning: A Technical Review	120
GenPoly: Learning Generalized and Tessellated Shape Priors via 3D Polymorphic Evolving	120
Knowledge-Based Embodied Question Answering	119
Self-Supervised Multimodal Learning: A Survey	119
Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey	118
P2T: Pyramid Pooling Transformer for Scene Understanding	118
Low-Shot Video Object Segmentation	117
JointFormer: A Unified Framework With Joint Modeling for Video Object Segmentation	117
ComputingEdge ad	117
WildVideo: Benchmarking LMMs for Understanding Video-Language Interaction	116
Cover 3	115
Supervision by Denoising	114
Towards Reliable and Faithful Explanations: A Disentanglement-Augmented Approach for Selective Rationalization	114
Reframing Neural Networks: Deep Structure in Overcomplete Representations	114
Noisy Label Learning With Provable Consistency for a Wider Family of Losses	114
On the Universal Approximation Properties of Deep Neural Networks Using MAM Neurons	114
PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference	113
PMGT-VR: A Decentralized Proximal-Gradient Algorithmic Framework With Variance Reduction	113
SS-NeRF: Physically Based Sparse Spectral Rendering With Neural Radiance Field	113
AutoEval: Are Labels Always Necessary for Classifier Accuracy Evaluation?	113
Cascaded Dynamic Memory Refinement and Semantic Alignment for Exo-to-Ego Cross-View Video Generation	111
iSeg: An Iterative Refinement-based Framework for Training-free Segmentation	111
Distributionally Location-Aware Transferable Adversarial Patches for Facial Images	111
Deep Learning on Object-Centric 3D Neural Fields	111
RGB-T Tracking With Template-Bridged Search Interaction and Target-Preserved Template Updating	108
Pair Then Relation: Pair-Net for Panoptic Scene Graph Generation	108
Adversarially Robust Neural Architectures	108
MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video	106
GLC++: Source-Free Universal Domain Adaptation Through Global-Local Clustering and Contrastive Affinity Learning	106
SHADOW: Secure Hidden Authenticating Digital Objects in the Wild	106
Learn to Enhance Sparse Spike Streams	105
NuwaDynamics+: A Causality-Aware Generative Framework for Spatio-Temporal Representation Learning	104
Pixel Distillation: Cost-Flexible Distillation Across Image Sizes and Heterogeneous Networks	103
ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning	103
An Energy-Based Prior for Generative Saliency	102
Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding	102
The Cluster Structure Function	102
Semi-Supervised Learning for FGVC With Out-of-Category Data	102
Heterogeneous Feature Re-Sampling for Balanced Pedestrian Attribute Recognition	101
Editorial: Special Section on Egocentric Perception	101
Reusable Architecture Growth for Continual Stereo Matching	100
Stimulative Training++: Go Beyond the Performance Limits of Residual Networks	100
Generalized Task-Driven Medical Image Quality Enhancement With Gradient Promotion	99
Learning With Constraint Learning: New Perspective, Solution Strategy and Various Applications	99
Continual Unsupervised Generative Modeling	99
Learning to Super-Resolve Blurry Images With Events	99
Compositional Physical Reasoning of Objects and Events From Videos	99
DeepMesh: Differentiable Iso-Surface Extraction	99
STAR-FC: Structure-Aware Face Clustering on Ultra-Large-Scale Graphs	98
Joint Framework for Single Image Reconstruction and Super-Resolution With an Event Camera	98
Any Fashion Attribute Editing: Dataset and Pretrained Models	98
Reinforcing Generated Images via Meta-Learning for One-Shot Fine-Grained Visual Recognition	98
An Algebraic Geometry Approach to Viewing Graph Solvability	97
Test-Time Training for Hyperspectral Image Super-Resolution	97
Orthogonal Decoupling Contrastive Regularization: Toward Uncorrelated Feature Decoupling for Unpaired Image Restoration	96
A Thorough Benchmark and a New Model for Light Field Saliency Detection	96
Temporal Stereo Matching From Event Cameras via Joint Learning With Stereoscopic Flow	95
GhostingNet: A Novel Approach for Glass Surface Detection With Ghosting Cues	94
Dynamic Differential Image Circle Diameter Measurement Precision Assessment: Application to Burning Droplets	94
Confidence-Aware Pseudo-Label Self-Correction for Weakly Supervised Visual Grounding	94
Relationship Quantification of Image Degradations	94
Adaptive Sparse Self-Attention for Efficient Image Super-resolution and beyond	94
Human as Points: Explicit Point-Based 3D Human Reconstruction From Single-View RGB Images	94
3D Visual Saliency: An Independent Perceptual Measure or a Derivative of 2D Image Saliency?	93
RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging	93
Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses	93
SKDF: A Simple Knowledge Distillation Framework for Distilling Open-Vocabulary Knowledge to Open-World Object Detector	92
CC4S: Encouraging Certainty and Consistency in Scribble-Supervised Semantic Segmentation	91
CycMuNet+: Cycle-Projected Mutual Learning for Spatial-Temporal Video Super-Resolution	91
Compositional Generative Model of Unbounded 4D Cities	91
Scale Propagation Network for Generalizable Depth Completion	90
Multi-Modality Multi-Attribute Contrastive Pre-Training for Image Aesthetics Computing	90
Conformal Prediction for Time Series	90
S$^{2}$ 2O: Enhancing Adversarial Training With Second-Order Statistics of Weights	89
SS-TBN: A Semi-Supervised Tri-Branch Network for COVID-19 Screening and Lesion Segmentation	88
Adaptive Perspective Distillation for Semantic Segmentation	88
$\mathcal {X}$-Metric: An N-Dimensional Information-Theoretic Framework for Groupwise Registration and Deep Combined Computing	86
Unified Adversarial Patch for Visible-Infrared Cross-Modal Attacks in the Physical World	86