OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 145. 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 2022-08-01 to 2026-08-01.)

Article	Citations
Front Cover	4106
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search	2169
Editorial: Introduction to the Special Section on Best of CVPR'2022	1708
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach	1120
Video Demoireing Using Focused-Defocused Dual-Camera System	979
A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization	865
Towards Accurate and Compact Architectures via Neural Architecture Transformer	855
Seeing Through Satellite Images at Street Views	833
Next Bit Prediction: A Unified Lossless and Lossy Point Cloud Geometry Compression Framework	828
Modeling Noisy Annotations for Point-Wise Supervision	752
Test-Time Correction: An Online 3D Detection System via Visual Prompting	707
Reliable and Compact Graph Fine-Tuning Via Graph Sparse Prompting	667
Event-Based Photometric Bundle Adjustment	654
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	649
Rethinking Link Prediction for Directed Graphs	628
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	624
Rethinking Rotation-Invariant Recognition of Fine-Grained Shapes From the Perspective of Contour Points	581
Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective	578
MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning	577
Quadratic Matrix Factorization With Applications to Manifold Learning	568
Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting	554
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference	541
Like Human Rethinking: Contour Transformer AutoRegression for Referring Remote Sensing Interpretation	539
A Personalized and Privacy-Preserving Federated Transformer Framework for Multilingual Sentiment Analysis	521
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation	506

Graph Convolutional Module for Temporal Action Localization in Videos	490
Face Forgery Detection by 3D Decomposition and Composition Search	488
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning	486
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus	476
Learning to Guide a Saturation-Based Theorem Prover	475
Moment-Reenacting: Inverse Motion Degradation With Cross-Shutter Guidance	454
SNI-SLAM++: Tightly-Coupled Semantic Neural Implicit SLAM	454
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	453
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration	452
Improving Viewpoint Robustness for Visual Recognition via Adversarial Training	442
Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations	438
Enhancing Representations Through Heterogeneous Self-Supervised Learning	430
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	429
A Clustering Validity Index With Multi-Granularity Fusion for Multiple Fuzzy Clustering Algorithms	426
LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting	413
Prior Image Guided Snapshot Compressive Spectral Imaging	408
Are Graph Convolutional Networks With Random Weights Feasible?	393
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	383
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing	357
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	346
Label Hierarchy Transition: Delving Into Class Hierarchies to Enhance Deep Classifiers	342
SCGT: Toward Scalable and Comprehensive Graph Transformer	338
XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition	336
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	329
Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching	328
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	322
SymBOL: A General-Purpose Symbolic Learner for Scientific Discovery Using Bayesian Optimization-Enhanced Large Language Models	317
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks	315
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	315
Invariant Policy Learning: A Causal Perspective	311
Simplicial Complex Neural Networks	304
Locating and Counting Heads in Crowds With a Depth Prior	304
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	303
Affective Image Content Analysis: Two Decades Review and New Perspectives	300
BiBBDM: Bidirectional Image Translation With Brownian Bridge Diffusion Models	298
Interactive NeRF Geometry Editing With Shape Priors	293
Rein++: Efficient Generalization and Adaptation for Semantic Segmentation With Vision Foundation Models	290
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	290
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition	289
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	283
VATr++: Choose Your Words Wisely for Handwritten Text Generation	283
Self-Supervised Skeleton Representation Learning Via Actionlet Contrast and Reconstruct	279
Deep Long-Tailed Learning: A Survey	277
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models	273
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting	270
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	262
Active Supervised Cross-Modal Retrieval	257
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data	256
Learn to Predict Sets Using Feed-Forward Neural Networks	254
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification	253

Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification	252
Face Generation and Editing With StyleGAN: A Survey	251
Centerless Clustering	248
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	245
On the Trade-Off Between Flatness and Optimization in Distributed Learning	244
A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation	244
Transformer-Based Visual Segmentation: A Survey	241
Physics-Informed Guided Disentanglement in Generative Networks	240
Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes	239
Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures	239
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	236
Structure-Preserving Image Super-Resolution	235
AIRPNet: Adaptive Image Restoration With Privacy Protection in Steganographic Domain	229
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	225
Towards Unified Deep Image Deraining: A Survey and a New Benchmark	224
Cover 2	221
Rate-Distortion Theory in Coding for Machines and Its Applications	216
Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation	215
Human Interaction Understanding With Consistency-Aware Learning	213
Learning Graph Attentions via Replicator Dynamics	212
Continuous Review and Timely Correction: Enhancing the Resistance to Noisy Labels via Self-Not-True and Class-Wise Distillation	212
On Positive-Unlabeled Classification From Corrupted Data in GANs	210
A Unified Experience Replay Framework for Spiking Deep Reinforcement Learning	205
Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration	200
Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes for Pruning is Possible Without Retraining	197
Curriculum-Based Asymmetric Multi-Task Reinforcement Learning	197
Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition	194
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning	194
Compositional Scene Representation Learning via Reconstruction: A Survey	190
Thermal3D-GS: Physics-Induced 3D Gaussians for Thermal Infrared Novel-View Synthesis With a Large-Scale Dataset	189
Autonomous Causal Discovery: Evaluating LLMs' Priors and Constraint Strategies for Reliability	188
MESA: Effective Matching Redundancy Reduction by Semantic Area Segmentation	188
Scanpath Prediction in Panoramic Videos Via Expected Code Length Minimization	187
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos	186
M$^{3}$3D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-Level Information Extraction	185
Universal Image Segmentation With Efficiency	179
SPLiT: Single Portrait Lighting Estimation via a Tetrad of Face Intrinsics	178
Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification	178
Learning Efficient Meshflow and Optical Flow From Event Cameras	178
LMP-GAN: Out-of-Distribution Detection for Non-Control Data Malware Attacks	177
InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis With Semantic Graph Prior	177
Discriminant Feature Extraction by Generalized Difference Subspace	177
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration	176
Single-Stage Instance Segmentation Survey: A “1+2+3” Technical Framework	175
Image-to-Image Translation With Disentangled Latent Vectors for Face Editing	174
Supervised Small-Baseline and Large-Baseline Homography Learning With Diffusion-Based Data Generation	173
Deciphering Object Concepts: Hierarchical Cross-Modal Relational Reasoning for Mining Object-Attribute-Affordance Associations	172
Privacy Preserving Decentralized Learning With Positive-Incentive Noise	172
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation	171
GenPoly: Learning Generalized and Tessellated Shape Priors via 3D Polymorphic Evolving	170
Graph-Oriented Instruction Tuning of Large Language Models for Generic Graph Mining	168
Physics-Informed Matrix Factorization Operator	168
EVDI++: Event-based Video Deblurring and Interpolation via Self-Supervised Learning	166
GradMDM: Adversarial Attack on Dynamic Networks	166
Adaptive Transfer Kernel Learning for Transfer Gaussian Process Regression	164
Reduced-Rank Tensor-on-Tensor Regression and Tensor-Variate Analysis of Variance	163
A Unified Decision Rule for Generalized Out-of-Distribution Detection	163
SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration	162
Human-Centric Transformer for Domain Adaptive Action Recognition	155
Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification	153
Image Lens Flare Removal Using Adversarial Curve Learning	150
Learning to See Through With Events	149
Knowledge-Based Embodied Question Answering	148
Winsor-CAM: Human-Tunable Visual Explanations From Deep Networks via Layer-Wise Winsorization	148
Learning From Partially Labeled Data for Multi-Organ and Tumor Segmentation	147
GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector	147
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning	146
A New Brain Network Construction Paradigm for Brain Disorder via Diffusion-Based Graph Contrastive Learning	146
Unbiased Scene Graph Generation via Two-Stage Causal Modeling	145
To Fold or Not to Fold: Graph Regularized Tensor Train for Visual Data Completion	145
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation	145
Self-Supervised Multimodal Learning: A Survey	145