IEEE Transactions on Pattern Analysis and Machine Intelligence

Article	Citations
Learn to Predict Sets Using Feed-Forward Neural Networks	3038
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification	2731
Modeling Noisy Annotations for Point-Wise Supervision	1527
[Back cover - Table of contents, continued]	1503
Front Cover	1400
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference	1392
Self-Supervised Skeleton Representation Learning via Actionlet Contrast and Reconstruct	1390
A Generative Model for Generic Light Field Reconstruction	1265
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification	1263
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation	1059
Centerless Clustering	1007
Video Demoireing using Focused-Defocused Dual-Camera System	892
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing	722
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	690
Deep Non-Rigid Structure From Motion With Missing Data	649
Affective Image Content Analysis: Two Decades Review and New Perspectives	611
Simplicial Complex Neural Networks	583
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search	537
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	523
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	509
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	506
Locating and Counting Heads in Crowds With a Depth Prior	506
Invariant Policy Learning: A Causal Perspective	470
Quadratic Matrix Factorization With Applications to Manifold Learning	453
Enhancing Representations Through Heterogeneous Self-Supervised Learning	445

A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization	445
Unsupervised Domain Adaptation via Discriminative Manifold Propagation	441
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data	439
BiBBDM: Bidirectional Image Translation with Brownian Bridge Diffusion Models	427
Physics-Informed Guided Disentanglement in Generative Networks	411
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	410
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration	402
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	400
Prior Image Guided Snapshot Compressive Spectral Imaging	385
Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting	376
Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes	376
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	374
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	372
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	367
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models	357
Towards Accurate and Compact Architectures via Neural Architecture Transformer	339
Interactive NeRF Geometry Editing With Shape Priors	336
Graph Convolutional Module for Temporal Action Localization in Videos	335
ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks	332
Active Supervised Cross-Modal Retrieval	326
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach	324
Instance Shadow Detection with A Single-Stage Detector	320
Towards Unified Deep Image Deraining: A Survey and a New Benchmark	320
On the Trade-Off Between Flatness and Optimization in Distributed Learning	318
Event-Based Photometric Bundle Adjustment	313
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	312
VATr++: Choose Your Words Wisely for Handwritten Text Generation	303
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting	297
Learning to Guide a Saturation-Based Theorem Prover	295
Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures	295
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition	292
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	290
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus	286
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning	277
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks	264
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks	258
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	249
A Clustering Validity Index With Multi-Granularity Fusion for Multiple Fuzzy Clustering Algorithms	247
Structure-Preserving Image Super-Resolution	247
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	245
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	242
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	241
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	240
Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching	231
Are Graph Convolutional Networks With Random Weights Feasible?	231
Deep Long-Tailed Learning: A Survey	225
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	224
Transformer-Based Visual Segmentation: A Survey	221
Face Forgery Detection by 3D Decomposition and Composition Search	218
Inferring Point Cloud Quality via Graph Similarity	213

Face Generation and Editing With StyleGAN: A Survey	212
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	211
Fast Component Tree Computation for Images of Limited Levels	202
Human-Centric Transformer for Domain Adaptive Action Recognition	200
Cover 2	198
Cover	197
Cover	197
Table of Contents	196
IEEE Computer Society Has You Covered!	196
TPAMI Information for Authors	195
A Variational EM Acceleration for Efficient Clustering at Very Large Scales	195
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation	192
Discriminant Feature Extraction by Generalized Difference Subspace	192
Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation	190
LMP-GAN: Out-of-Distribution Detection for Non-Control Data Malware Attacks	190
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation	190
On Positive-Unlabeled Classification From Corrupted Data in GANs	189
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks	187
Rate-Distortion Theory in Coding for Machines and Its Applications	186
Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes for Pruning is Possible Without Retraining	186
InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis with Semantic Graph Prior	182
Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification	180
Curriculum-Based Asymmetric Multi-Task Reinforcement Learning	179
Power Normalizations in Fine-Grained Image, Few-Shot Image and Graph Classification	178
SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration	177
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning	174
Reduced-Rank Tensor-on-Tensor Regression and Tensor-Variate Analysis of Variance	173
Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights	171
Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition	171
AutoNovel: Automatically Discovering and Learning Novel Visual Categories	167
Orientational Distribution Learning with Hierarchical Spatial Attention for Open Set Recognition	165
Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining	161
Inter-Intra Hypergraph Computation for Survival Prediction on Whole Slide Images	161
Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey	161
Out-of-Domain Generalization From a Single Source: An Uncertainty Quantification Approach	159
HiGCIN: Hierarchical Graph-Based Cross Inference Network for Group Activity Recognition	155
M3D: a Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information Extraction	154
Universal Image Segmentation With Efficiency	153
Temporal Feature Matters: A Framework for Diffusion Model Quantization	152
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration	152
Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation	152
BNET: Batch Normalization With Enhanced Linear Transformation	149
On the Robustness of Average Losses for Partial-Label Learning	146
Dynamic Self-Supervised Teacher-Student Network Learning	146
SPLiT: Single Portrait Lighting Estimation via a Tetrad of Face Intrinsics	144
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos	144
Deep Learning-Based Point Cloud Compression: An In-Depth Survey and Benchmark	142
Self-Scalable Tanh (Stan): Multi-Scale Solutions for Physics-Informed Neural Networks	142
Compositional Scene Representation Learning via Reconstruction: A Survey	142
Image Lens Flare Removal Using Adversarial Curve Learning	141
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks	141
GenPoly: Learning Generalized and Tessellated Shape Priors via 3D Polymorphic Evolving	141
Correcting Optical Aberration via Depth-Aware Point Spread Functions	140
Learning Graph Attentions via Replicator Dynamics	138
Human Interaction Understanding With Consistency-Aware Learning	138
VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision	138
GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector	136
GradMDM: Adversarial Attack on Dynamic Networks	134
Learning to See Through With Events	133
Adaptive Transfer Kernel Learning for Transfer Gaussian Process Regression	133
Spatial-Temporal Transformer for Video Snapshot Compressive Imaging	133
Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond	131
Differential Viewpoints for Ground Terrain Material Recognition	131
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets	130
Enhancing Photorealism Enhancement	130
Learning Efficient Meshflow and Optical Flow from Event Cameras	130
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning	129
Interpretable Optimization-Inspired Unfolding Network for Low-Light Image Enhancement	127
Learning From Partially Labeled Data for Multi-Organ and Tumor Segmentation	126
Hypergraph-Based Multi-View Action Recognition Using Event Cameras	126
Differentially Private Graph Neural Networks for Whole-Graph Classification	124
Asymmetric Loss Functions for Noise-Tolerant Learning: Theory and Applications	122
PathNet: Path-Selective Point Cloud Denoising	122
Self-Supervised Multimodal Learning: A Survey	120
A New Brain Network Construction Paradigm for Brain Disorder via Diffusion-Based Graph Contrastive Learning	119
Fear-Neuro-Inspired Reinforcement Learning for Safe Autonomous Driving	117
Variational Data-Free Knowledge Distillation for Continual Learning	117
Unbiased Scene Graph Generation via Two-Stage Causal Modeling	117
Deep Gait Recognition: A Survey	116
Deep Learning for Face Anti-Spoofing: A Survey	116

Random Permutation Set Reasoning	116
Revisiting Nonlocal Self-Similarity from Continuous Representation	115
MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion	115
Image-to-Image Translation With Disentangled Latent Vectors for Face Editing	113
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses	112
MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning	111
Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification	111
Knowledge-Based Embodied Question Answering	111
Domain Generalization: A Survey	111
Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap	110
A Style-Based Generator Architecture for Generative Adversarial Networks	110
To Fold or Not to Fold: Graph Regularized Tensor Train for Visual Data Completion	109
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking	108
Accurate and Efficient Stereo Matching via Attention Concatenation Volume	107
Advances and Challenges in Meta-Learning: A Technical Review	107
MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network	107
From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing	106
A Fully Automated Method for 3D Individual Tooth Identification and Segmentation in Dental CBCT	106
ComputingEdge ad	106
P2T: Pyramid Pooling Transformer for Scene Understanding	106
STAR-FC: Structure-Aware Face Clustering on Ultra-Large-Scale Graphs	105
Relationship Quantification of Image Degradations	104
The Bayesian Cut	104
Stimulative Training++: Go Beyond the Performance Limits of Residual Networks	103
Continual Unsupervised Generative Modeling	103
Deciphering the Feature Representation of Deep Neural Networks for High-Performance AI	102
Towards Reliable and Faithful Explanations: A Disentanglement-Augmented Approach for Selective Rationalization	102
Learning With Constraint Learning: New Perspective, Solution Strategy and Various Applications	102
Probabilistic Directed Distance Fields for Ray-Based Shape Representations	102
Homeomorphism Prior for False Positive and Negative Problem in Medical Image Dense Contrastive Representation Learning	101
Semi-Supervised Learning for FGVC With Out-of-Category Data	101
Low-Shot Video Object Segmentation	100
JointFormer: A Unified Framework With Joint Modeling for Video Object Segmentation	99
Dynamic Differential Image Circle Diameter Measurement Precision Assessment: Application to Burning Droplets	99
Cover 3	99
Multi-Modality Multi-Attribute Contrastive Pre-Training for Image Aesthetics Computing	99
The Cluster Structure Function	98
An Energy-Based Prior for Generative Saliency	98
Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding	98
Editorial: Special Section on Egocentric Perception	98
Pixel Distillation: Cost-Flexible Distillation Across Image Sizes and Heterogeneous Networks	97
Reusable Architecture Growth for Continual Stereo Matching	97
Scale Propagation Network for Generalizable Depth Completion	97
Compositional Physical Reasoning of Objects and Events From Videos	96
Deep Learning on Object-Centric 3D Neural Fields	95
TE141K: Artistic Text Benchmark for Text Effect Transfer	95
Generalized Task-Driven Medical Image Quality Enhancement With Gradient Promotion	95
GhostingNet: A Novel Approach for Glass Surface Detection With Ghosting Cues	95
Learning to Super-Resolve Blurry Images With Events	95
AutoEval: Are Labels Always Necessary for Classifier Accuracy Evaluation?	94
MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video	94
Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation	94
FreeFusion: Infrared and Visible Image Fusion via Cross Reconstruction Learning	94
On the Universal Approximation Properties of Deep Neural Networks Using MAM Neurons	93
Point Spatio-Temporal Transformer Networks for Point Cloud Video Modeling	93
Test-Time Training for Hyperspectral Image Super-Resolution	93
Cascaded Dynamic Memory Refinement and Semantic Alignment for Exo-to-Ego Cross-View Video Generation	93
GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning	93
Compositional Generative Model of Unbounded 4D Cities	92
ONNXPruner: ONNX-Based General Model Pruning Adapter	91
Optimizing Regularized Cholesky Score for Order-Based Learning of Bayesian Networks	90
Hypergraph-Based High-Order Correlation Analysis for Large-Scale Long-Tailed Data Classification	90
Distributionally Location-Aware Transferable Adversarial Patches for Facial Images	90
Heterogeneous Feature Re-Sampling for Balanced Pedestrian Attribute Recognition	89
Adaptive Perspective Distillation for Semantic Segmentation	89
Improving Machine Vision Using Human Perceptual Representations: The Case of Planar Reflection Symmetry for Object Classification	89
SKDF: A Simple Knowledge Distillation Framework for Distilling Open-Vocabulary Knowledge to Open-world Object Detector	89
PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference	88
PMGT-VR: a Decentralized Proximal-gradient Algorithmic Framework with Variance Reduction	88
WildVideo: Benchmarking LMMs for Understanding Video-Language Interaction	87
Reinforcing Generated Images via Meta-Learning for One-Shot Fine-Grained Visual Recognition	87
Any Fashion Attribute Editing: Dataset and Pretrained Models	87
Adversarially Robust Neural Architectures	87
Semantic Object Accuracy for Generative Text-to-Image Synthesis	86
CC4S: Encouraging Certainty and Consistency in Scribble-Supervised Semantic Segmentation	86
TN-ZSTAD: Transferable Network for Zero-Shot Temporal Activity Detection	86
Unified Modality Separation: A Vision-Language Framework for Unsupervised Domain Adaptation	86
3D Visual Saliency: An Independent Perceptual Measure or a Derivative of 2D Image Saliency?	86
luvHarris: A Practical Corner Detector for Event-Cameras	86
Self-Guidance: Boosting Flow and Diffusion Generation on Their Own	85
SS-NeRF: Physically Based Sparse Spectral Rendering with Neural Radiance Field	85
Human as Points: Explicit Point-Based 3D Human Reconstruction From Single-View RGB Images	85
Pair Then Relation: Pair-Net for Panoptic Scene Graph Generation	85
RGB-T Tracking With Template-Bridged Search Interaction and Target-Preserved Template Updating	85
Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization	84
Recurrent Neural Networks for Snapshot Compressive Imaging	83
DeepMesh: Differentiable Iso-Surface Extraction	83
Support Vector Machine Classifier via Soft-Margin Loss	83
Conformal Prediction for Time Series	82
Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset	82
ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning	82
Noisy Label Learning With Provable Consistency for a Wider Family of Losses	82
Reframing Neural Networks: Deep Structure in Overcomplete Representations	82
Joint Framework for Single Image Reconstruction and Super-Resolution With an Event Camera	82
RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging	81