OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 133. 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 2021-11-01 to 2025-11-01.)

Article	Citations
[Back cover - Table of contents, continued]	2904
Front Cover	1584
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference	1535
Learn to Predict Sets Using Feed-Forward Neural Networks	1471
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification	1449
Modeling Noisy Annotations for Point-Wise Supervision	1436
Video Demoireing using Focused-Defocused Dual-Camera System	1283
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	1095
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	1078
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search	931
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	748
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	715
Physics-Informed Guided Disentanglement in Generative Networks	686
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks	603
Towards Accurate and Compact Architectures via Neural Architecture Transformer	555
A Generative Model for Generic Light Field Reconstruction	541
Face Generation and Editing With StyleGAN: A Survey	541
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	536
MECD+ : Unlocking Event-Level Causal Graph Discovery for Video Reasoning	519
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition	485
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration	475
Structure-Preserving Image Super-Resolution	471
Face Forgery Detection by 3D Decomposition and Composition Search	460
Inferring Point Cloud Quality via Graph Similarity	446
Transformer-Based Visual Segmentation: A Survey	446

Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes	442
Affective Image Content Analysis: Two Decades Review and New Perspectives	432
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	430
A Clustering Validity Index With Multi-Granularity Fusion for Multiple Fuzzy Clustering Algorithms	425
ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks	411
Active Supervised Cross-Modal Retrieval	398
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus	391
Event-Based Photometric Bundle Adjustment	387
On the Trade-Off Between Flatness and Optimization in Distributed Learning	382
Instance Shadow Detection with A Single-Stage Detector	380
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning	360
VATr++: Choose Your Words Wisely for Handwritten Text Generation	355
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach	354
Interactive NeRF Geometry Editing With Shape Priors	352
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	350
A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization	350
Enhancing Representations Through Heterogeneous Self-Supervised Learning	349
Quadratic Matrix Factorization With Applications to Manifold Learning	343
Invariant Policy Learning: A Causal Perspective	340
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	339
Centerless Clustering	332
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	324
Deep Non-Rigid Structure From Motion With Missing Data	322
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data	316
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	309
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks	307
Unsupervised Domain Adaptation via Discriminative Manifold Propagation	301
Graph Convolutional Module for Temporal Action Localization in Videos	300
Simplicial Complex Neural Networks	300
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	299
Towards Unified Deep Image Deraining: A Survey and a New Benchmark	272
Editorial: Introduction to the Special Section on Best of CVPR'2022	272
Self-Supervised Skeleton Representation Learning Via Actionlet Contrast and Reconstruct	266
BiBBDM: Bidirectional Image Translation With Brownian Bridge Diffusion Models	259
Locating and Counting Heads in Crowds With a Depth Prior	255
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models	250
Are Graph Convolutional Networks With Random Weights Feasible?	248
Learning to Guide a Saturation-Based Theorem Prover	248
Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures	245
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing	245
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	237
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation	234
Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching	232
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification	231
Prior Image Guided Snapshot Compressive Spectral Imaging	227
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	222
Deep Long-Tailed Learning: A Survey	220
Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective	219
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting	218
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	212

Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	210
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	207
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	206
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	206
Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting	206
IEEE Computer Society Has You Covered!	204
Cover	203
Cover	202
Table of Contents	202
Cover 2	201
Fast Component Tree Computation for Images of Limited Levels	200
BNET: Batch Normalization With Enhanced Linear Transformation	197
Human-Centric Transformer for Domain Adaptive Action Recognition	197
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration	196
Universal Image Segmentation With Efficiency	196
M³D: a Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information Extraction	194
Temporal Feature Matters: A Framework for Diffusion Model Quantization	194
Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining	191
Spatial-Temporal Transformer for Video Snapshot Compressive Imaging	188
Learning to See Through With Events	186
Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights	184
SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration	183
InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis with Semantic Graph Prior	179
Rate-Distortion Theory in Coding for Machines and Its Applications	178
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning	174
Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation	172
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation	172
LMP-GAN: Out-of-Distribution Detection for Non-Control Data Malware Attacks	170
On Positive-Unlabeled Classification From Corrupted Data in GANs	169
Learning Graph Attentions via Replicator Dynamics	168
Human Interaction Understanding With Consistency-Aware Learning	163
Image Lens Flare Removal Using Adversarial Curve Learning	163
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks	163
GradMDM: Adversarial Attack on Dynamic Networks	161
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos	160
Revisiting Nonlocal Self-Similarity from Continuous Representation	159
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets	158
Enhancing Photorealism Enhancement	156
GenPoly: Learning Generalized and Tessellated Shape Priors via 3D Polymorphic Evolving	156
Knowledge-Based Embodied Question Answering	155
To Fold or Not to Fold: Graph Regularized Tensor Train for Visual Data Completion	154
Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification	151
GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector	149
A New Brain Network Construction Paradigm for Brain Disorder via Diffusion-Based Graph Contrastive Learning	148
Learning Efficient Meshflow and Optical Flow from Event Cameras	146
Out-of-Domain Generalization From a Single Source: An Uncertainty Quantification Approach	146
PathNet: Path-Selective Point Cloud Denoising	145
Adaptive Transfer Kernel Learning for Transfer Gaussian Process Regression	143
Differential Viewpoints for Ground Terrain Material Recognition	143
Self-Scalable Tanh (Stan): Multi-Scale Solutions for Physics-Informed Neural Networks	142
SPLiT: Single Portrait Lighting Estimation via a Tetrad of Face Intrinsics	141
Reduced-Rank Tensor-on-Tensor Regression and Tensor-Variate Analysis of Variance	140
Deep Learning-Based Point Cloud Compression: An In-Depth Survey and Benchmark	140
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning	138
Power Normalizations in Fine-Grained Image, Few-Shot Image and Graph Classification	137
Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification	136
A Variational EM Acceleration for Efficient Clustering at Very Large Scales	136
On the Robustness of Average Losses for Partial-Label Learning	133
Correcting Optical Aberration via Depth-Aware Point Spread Functions	133
Accurate and Efficient Stereo Matching via Attention Concatenation Volume	133
Orientational Distribution Learning with Hierarchical Spatial Attention for Open Set Recognition	133