OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 144. 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 2022-06-01 to 2026-06-01.)

Article	Citations
Front Cover	3833
On the Trade-Off Between Flatness and Optimization in Distributed Learning	1991
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search	1709
Editorial: Introduction to the Special Section on Best of CVPR'2022	1562
Self-Supervised Skeleton Representation Learning Via Actionlet Contrast and Reconstruct	984
BiBBDM: Bidirectional Image Translation With Brownian Bridge Diffusion Models	916
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach	774
Video Demoireing Using Focused-Defocused Dual-Camera System	742
Invariant Policy Learning: A Causal Perspective	731
A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization	728
Towards Accurate and Compact Architectures via Neural Architecture Transformer	686
Seeing Through Satellite Images at Street Views	682
Next Bit Prediction: A Unified Lossless and Lossy Point Cloud Geometry Compression Framework	669
LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting	627
Modeling Noisy Annotations for Point-Wise Supervision	609
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	608
Test-Time Correction: An Online 3D Detection System via Visual Prompting	602
Simplicial Complex Neural Networks	591
Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures	554
Rethinking Rotation-Invariant Recognition of Fine-Grained Shapes From the Perspective of Contour Points	548
Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective	538
MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning	532
Quadratic Matrix Factorization With Applications to Manifold Learning	529
Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting	508
Learn to Predict Sets Using Feed-Forward Neural Networks	504

Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing	490
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	460
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference	458
Like Human Rethinking: Contour Transformer AutoRegression for Referring Remote Sensing Interpretation	450
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	450
A Personalized and Privacy-Preserving Federated Transformer Framework for Multilingual Sentiment Analysis	444
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	437
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification	435
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data	433
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus	430
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification	418
VATr++: Choose Your Words Wisely for Handwritten Text Generation	418
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	394
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	392
AIRPNet: Adaptive Image Restoration With Privacy Protection in Steganographic Domain	386
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	382
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting	380
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation	377
Graph Convolutional Module for Temporal Action Localization in Videos	373
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	371
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks	357
Enhancing Representations Through Heterogeneous Self-Supervised Learning	353
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	336
Centerless Clustering	313
Active Supervised Cross-Modal Retrieval	310
Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Models	309
Are Graph Convolutional Networks With Random Weights Feasible?	308
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	302
Reliable and Compact Graph Fine-Tuning Via Graph Sparse Prompting	300
Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers	298
SCGT: Towards Scalable and Comprehensive Graph Transformer	296
Event-Based Photometric Bundle Adjustment	295
Locating and Counting Heads in Crowds With a Depth Prior	289
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	288
Rethinking Link Prediction for Directed Graphs	287
Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes	278
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	278
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	271
Deep Long-Tailed Learning: A Survey	270
Physics-Informed Guided Disentanglement in Generative Networks	270
Learning to Guide a Saturation-Based Theorem Prover	265
Face Generation and Editing With StyleGAN: A Survey	263
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning	262
Interactive NeRF Geometry Editing With Shape Priors	252
Prior Image Guided Snapshot Compressive Spectral Imaging	252
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition	251
Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations	238
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	236
Moment-Reenacting: Inverse Motion Degradation With Cross-Shutter Guidance	234
SNI-SLAM++: Tightly-Coupled Semantic Neural Implicit SLAM	234

A Clustering Validity Index With Multi-Granularity Fusion for Multiple Fuzzy Clustering Algorithms	233
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration	232
Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching	231
Affective Image Content Analysis: Two Decades Review and New Perspectives	230
Towards Unified Deep Image Deraining: A Survey and a New Benchmark	230
Structure-Preserving Image Super-Resolution	229
Transformer-Based Visual Segmentation: A Survey	229
Inferring Point Cloud Quality via Graph Similarity	227
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	224
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	223
Face Forgery Detection by 3D Decomposition and Composition Search	222
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models	220
Cover 2	219
BNET: Batch Normalization With Enhanced Linear Transformation	218
Adaptive Transfer Kernel Learning for Transfer Gaussian Process Regression	217
Rate-Distortion Theory in Coding for Machines and Its Applications	214
Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation	210
SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration	208
EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning	205
Deep Orientational Representation Learning for Ordinal Regression	203
Graph-Oriented Instruction Tuning of Large Language Models for Generic Graph Mining	201
Human Interaction Understanding With Consistency-Aware Learning	201
Continuous Review and Timely Correction: Enhancing the Resistance to Noisy Labels via Self-Not-True and Class-Wise Distillation	196
Image Lens Flare Removal Using Adversarial Curve Learning	195
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning	193
Learning Graph Attentions via Replicator Dynamics	190
On Positive-Unlabeled Classification From Corrupted Data in GANs	186
A Variational EM Acceleration for Efficient Clustering at Very Large Scales	182
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets	180
Mining Association Patterns From Neighborhood Insight	179
Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights	177
GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector	177
Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization	177
Controllable Generation With Text-to-Image Diffusion Models: A Survey	177
HiGCIN: Hierarchical Graph-Based Cross Inference Network for Group Activity Recognition	175
Enhancing Photorealism Enhancement	173
A Unified Experience Replay Framework for Spiking Deep Reinforcement Learning	172
Learning to See Through With Events	171
Self-Scalable Tanh (Stan): Multi-Scale Solutions for Physics-Informed Neural Networks	170
A New Brain Network Construction Paradigm for Brain Disorder via Diffusion-Based Graph Contrastive Learning	170
Revisiting Nonlocal Self-Similarity from Continuous Representation	169
PathNet: Path-Selective Point Cloud Denoising	169
Image-to-Image Translation With Disentangled Latent Vectors for Face Editing	168
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation	168
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks	167
Human-Centric Transformer for Domain Adaptive Action Recognition	167
Random Permutation Set Reasoning	165
Variational Data-Free Knowledge Distillation for Continual Learning	165
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking	163
A Unified Decision Rule for Generalized Out-of-Distribution Detection	163
Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond	161
Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification	161
Temporal Feature Matters: A Framework for Diffusion Model Quantization	160
Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation	160
AutoNovel: Automatically Discovering and Learning Novel Visual Categories	160
Hypergraph-Based Multi-View Action Recognition Using Event Cameras	159
P2T: Pyramid Pooling Transformer for Scene Understanding	159
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos	158
Out-of-Domain Generalization From a Single Source: An Uncertainty Quantification Approach	157
Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes for Pruning is Possible Without Retraining	157
Curriculum-Based Asymmetric Multi-Task Reinforcement Learning	154
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation	154
Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey	154
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning	152
Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition	152
Compositional Scene Representation Learning via Reconstruction: A Survey	149
Reduced-Rank Tensor-on-Tensor Regression and Tensor-Variate Analysis of Variance	148
Differentially Private Graph Neural Networks for Whole-Graph Classification	147
Fear-Neuro-Inspired Reinforcement Learning for Safe Autonomous Driving	146