OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 134. 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 2022-01-01 to 2026-01-01.)

Article	Citations
[Back cover - Table of contents, continued]	3182
Front Cover	1690
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	1610
Editorial: Introduction to the Special Section on Best of CVPR'2022	1549
Self-Supervised Skeleton Representation Learning Via Actionlet Contrast and Reconstruct	1515
BiBBDM: Bidirectional Image Translation With Brownian Bridge Diffusion Models	1221
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	1171
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	982
MECD+ : Unlocking Event-Level Causal Graph Discovery for Video Reasoning	789
ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks	765
Active Supervised Cross-Modal Retrieval	611
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus	597
Event-Based Photometric Bundle Adjustment	577
On the Trade-Off Between Flatness and Optimization in Distributed Learning	576
VATr++: Choose Your Words Wisely for Handwritten Text Generation	546
Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective	534
Learning to Guide a Saturation-Based Theorem Prover	523
Towards Accurate and Compact Architectures via Neural Architecture Transformer	518
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration	496
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification	490
A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization	488
Enhancing Representations Through Heterogeneous Self-Supervised Learning	483
Quadratic Matrix Factorization With Applications to Manifold Learning	475
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	474
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	471

Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification	456
SNI-SLAM++: Tightly-Coupled Semantic Neural Implicit SLAM	455
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach	455
Video Demoireing Using Focused-Defocused Dual-Camera System	445
Instance Shadow Detection with A Single-Stage Detector	421
Rethinking Rotation-Invariant Recognition of Fine-grained Shapes from the Perspective of Contour Points	415
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation	413
Learn to Predict Sets Using Feed-Forward Neural Networks	394
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	393
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition	376
Test-time Correction: An Online 3D Detection System via Visual Prompting	371
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	370
Invariant Policy Learning: A Causal Perspective	368
Face Forgery Detection by 3D Decomposition and Composition Search	360
Locating and Counting Heads in Crowds With a Depth Prior	359
Physics-Informed Guided Disentanglement in Generative Networks	353
A Generative Model for Generic Light Field Reconstruction	353
Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting	342
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	341
A Clustering Validity Index With Multi-Granularity Fusion for Multiple Fuzzy Clustering Algorithms	338
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	334
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search	332
Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes	330
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting	319
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models	319
Graph Convolutional Module for Temporal Action Localization in Videos	315
Towards Unified Deep Image Deraining: A Survey and a New Benchmark	300
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	298
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning	283
Prior Image Guided Snapshot Compressive Spectral Imaging	270
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data	269
Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching	268
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	265
Interactive NeRF Geometry Editing With Shape Priors	264
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing	263
Structure-Preserving Image Super-Resolution	263
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	262
Modeling Noisy Annotations for Point-Wise Supervision	254
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	253
Inferring Point Cloud Quality via Graph Similarity	251
Simplicial Complex Neural Networks	247
Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures	247
Are Graph Convolutional Networks With Random Weights Feasible?	246
Centerless Clustering	240
Unsupervised Domain Adaptation via Discriminative Manifold Propagation	238
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks	236
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference	235
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	234
Face Generation and Editing With StyleGAN: A Survey	231
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	230

Deep Long-Tailed Learning: A Survey	229
Affective Image Content Analysis: Two Decades Review and New Perspectives	228
Transformer-Based Visual Segmentation: A Survey	225
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	221
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks	220
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	220
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	218
IEEE Computer Society Has You Covered!	215
Cover 2	212
Fast Component Tree Computation for Images of Limited Levels	212
BNET: Batch Normalization With Enhanced Linear Transformation	209
Universal Image Segmentation With Efficiency	208
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration	206
Temporal Feature Matters: A Framework for Diffusion Model Quantization	202
Spatial-Temporal Transformer for Video Snapshot Compressive Imaging	201
Learning to See Through With Events	198
Differential Viewpoints for Ground Terrain Material Recognition	197
Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights	194
Adaptive Transfer Kernel Learning for Transfer Gaussian Process Regression	191
Orientational Distribution Learning with Hierarchical Spatial Attention for Open Set Recognition	188
Graph-Oriented Instruction Tuning of Large Language Models for Generic Graph Mining	186
M3D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-Level Information Extraction	183
Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond	182
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks	181
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks	180
Random Permutation Set Reasoning	180
Learning From Partially Labeled Data for Multi-Organ and Tumor Segmentation	177
Power Normalizations in Fine-Grained Image, Few-Shot Image and Graph Classification	177
Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation	175
Image-to-Image Translation With Disentangled Latent Vectors for Face Editing	173
Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes for Pruning is Possible Without Retraining	172
Curriculum-Based Asymmetric Multi-Task Reinforcement Learning	171
Deep Learning for Face Anti-Spoofing: A Survey	170
Reduced-Rank Tensor-on-Tensor Regression and Tensor-Variate Analysis of Variance	169
Human-Centric Transformer for Domain Adaptive Action Recognition	164
AutoNovel: Automatically Discovering and Learning Novel Visual Categories	162
Inter-Intra Hypergraph Computation for Survival Prediction on Whole Slide Images	162
Out-of-Domain Generalization From a Single Source: An Uncertainty Quantification Approach	160
MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion	159
HiGCIN: Hierarchical Graph-Based Cross Inference Network for Group Activity Recognition	158
On the Robustness of Average Losses for Partial-Label Learning	157
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation	152
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning	152
On Positive-Unlabeled Classification From Corrupted Data in GANs	151
Human Interaction Understanding With Consistency-Aware Learning	150
GradMDM: Adversarial Attack on Dynamic Networks	150
InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis With Semantic Graph Prior	149
SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration	149
Learning Graph Attentions via Replicator Dynamics	148
Learning Efficient Meshflow and Optical Flow from Event Cameras	148
Image Lens Flare Removal Using Adversarial Curve Learning	147
To Fold or Not to Fold: Graph Regularized Tensor Train for Visual Data Completion	146
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos	146
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning	142
Deep Learning-Based Point Cloud Compression: An In-Depth Survey and Benchmark	141
GenPoly: Learning Generalized and Tessellated Shape Priors via 3D Polymorphic Evolving	139
SPLiT: Single Portrait Lighting Estimation via a Tetrad of Face Intrinsics	139
Dynamic Self-Supervised Teacher-Student Network Learning	139
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets	139