OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 122. 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 2021-05-01 to 2025-05-01.)

Article	Citations
Learn to Predict Sets Using Feed-Forward Neural Networks	2618
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus	2079
Time-Resolved Far Infrared Light Transport Decomposition for Thermal Photometric Stereo	1284
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data	1225
Learning to Guide a Saturation-Based Theorem Prover	1201
VATr++: Choose Your Words Wisely for Handwritten Text Generation	1151
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification	1131
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation	1110
Modeling Noisy Annotations for Point-Wise Supervision	1054
Face Forgery Detection by 3D Decomposition and Composition Search	1050
Invariant Policy Learning: A Causal Perspective	1022
Active Supervised Cross-Modal Retrieval	820
Cover	683
Editorial Board	664
[Back inside cover]	599
[Back cover - Table of contents, continued]	590
Front Cover	565
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach	537
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	485
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	483
A Generative Model for Generic Light Field Reconstruction	432
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	415
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing	412
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference	406
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	401

Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	391
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks	370
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	367
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	350
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	348
Deep Non-Rigid Structure From Motion With Missing Data	342
Instance Shadow Detection with A Single-Stage Detector	342
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	333
Physics-Informed Guided Disentanglement in Generative Networks	331
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search	323
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition	318
Enhancing Representations through Heterogeneous Self-Supervised Learning	317
Towards Accurate and Compact Architectures via Neural Architecture Transformer	312
Inferring Point Cloud Quality via Graph Similarity	308
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models	302
Quadratic Matrix Factorization With Applications to Manifold Learning	291
A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization	287
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	286
Towards Unified Deep Image Deraining: A Survey and A New Benchmark	283
Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures	282
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification	282
Transformer-Based Visual Segmentation: A Survey	277
Affective Image Content Analysis: Two Decades Review and New Perspectives	272
Are Graph Convolutional Networks With Random Weights Feasible?	270
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	268
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	263
Prior Image Guided Snapshot Compressive Spectral Imaging	254
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	251
Locating and Counting Heads in Crowds With a Depth Prior	250
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	249
ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks	244
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	230
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks	229
Interactive NeRF Geometry Editing With Shape Priors	224
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning	222
Centerless Clustering	215
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting	213
Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting	211
Graph Convolutional Module for Temporal Action Localization in Videos	204
Simplicial Complex Neural Networks	197
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	197
Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes	194
Structure-Preserving Image Super-Resolution	194
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	190
Face Generation and Editing With StyleGAN: A Survey	188
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	186
Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching	184
Deep Long-Tailed Learning: A Survey	183
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration	178
Unsupervised Domain Adaptation via Discriminative Manifold Propagation	177

Multi-Task Head Pose Estimation in-the-Wild	176
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation	173
Fast Component Tree Computation for Images of Limited Levels	172
Human-Centric Transformer for Domain Adaptive Action Recognition	169
Cover 2	168
Cover	168
Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation	167
Cover	166
Table of Contents	166
Cover	166
IEEE Computer Society Has You Covered!	165
Asymmetric Loss Functions for Noise-Tolerant Learning: Theory and Applications	164
Differentially Private Graph Neural Networks for Whole-Graph Classification	164
Orientational Distribution Learning with Hierarchical Spatial Attention for Open Set Recognition	163
TPAMI Information for Authors	161
Point Set Registration for 3D Range Scans Using Fuzzy Cluster-Based Metric and Efficient Global Optimization	160
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks	159
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning	159
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation	157
MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network	155
BNET: Batch Normalization With Enhanced Linear Transformation	155
Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond	155
Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene	154
VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision	154
Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition	150
AutoNovel: Automatically Discovering and Learning Novel Visual Categories	148
Differential Viewpoints for Ground Terrain Material Recognition	147
Compositional Scene Representation Learning via Reconstruction: A Survey	146
GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector	145
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets	143
Fear-Neuro-Inspired Reinforcement Learning for Safe Autonomous Driving	142
MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning	141
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
LMP-GAN: Out-Of-Distribution Detection For Non-Control Data Malware Attacks	134
Rate-Distortion Theory in Coding for Machines and its Applications	133
Interpretable Optimization-Inspired Unfolding Network for Low-Light Image Enhancement	133
Enhancing Photorealism Enhancement	132
Correcting Optical Aberration via Depth-Aware Point Spread Functions	131
Self-Scalable Tanh (Stan): Multi-Scale Solutions for Physics-Informed Neural Networks	131
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning	131
Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification	131
SPLiT: Single Portrait Lighting Estimation via a Tetrad of Face Intrinsics	130
From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing	129
Dynamic Self-Supervised Teacher-Student Network Learning	126
Hypergraph-Based Multi-View Action Recognition Using Event Cameras	126
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos	125
Learning Graph Attentions via Replicator Dynamics	122