OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 124. 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 2021-06-01 to 2025-06-01.)

Article	Citations
Learn to Predict Sets Using Feed-Forward Neural Networks	2703
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus	2202
Time-Resolved Far Infrared Light Transport Decomposition for Thermal Photometric Stereo	1318
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data	1275
Learning to Guide a Saturation-Based Theorem Prover	1234
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification	1173
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation	1171
Modeling Noisy Annotations for Point-Wise Supervision	1141
Face Forgery Detection by 3D Decomposition and Composition Search	1105
Invariant Policy Learning: A Causal Perspective	854
Cover	724
Editorial Board	711
[Back inside cover]	610
[Back cover - Table of contents, continued]	609
Front Cover	603
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	550
A Generative Model for Generic Light Field Reconstruction	511
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference	499
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	451
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	433
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	429
Deep Non-Rigid Structure From Motion With Missing Data	421
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	411
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search	392
Enhancing Representations through Heterogeneous Self-Supervised Learning	390

Quadratic Matrix Factorization With Applications to Manifold Learning	382
A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization	362
Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures	358
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks	354
Interactive NeRF Geometry Editing With Shape Priors	353
ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks	348
Towards Accurate and Compact Architectures via Neural Architecture Transformer	348
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	337
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration	331
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	331
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing	329
Graph Convolutional Module for Temporal Action Localization in Videos	320
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	316
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	309
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	305
Active Supervised Cross-Modal Retrieval	304
Unsupervised Domain Adaptation via Discriminative Manifold Propagation	295
Towards Unified Deep Image Deraining: A Survey and A New Benchmark	289
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification	289
Inferring Point Cloud Quality via Graph Similarity	287
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models	285
VATr++: Choose Your Words Wisely for Handwritten Text Generation	274
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	274
Locating and Counting Heads in Crowds With a Depth Prior	265
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach	262
Transformer-Based Visual Segmentation: A Survey	261
Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes	258
Structure-Preserving Image Super-Resolution	250
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	247
Centerless Clustering	242
Instance Shadow Detection with A Single-Stage Detector	233
Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching	229
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning	227
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	225
Face Generation and Editing With StyleGAN: A Survey	216
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	212
Physics-Informed Guided Disentanglement in Generative Networks	211
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	211
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	207
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks	204
Multi-Task Head Pose Estimation in-the-Wild	198
Are Graph Convolutional Networks With Random Weights Feasible?	197
Affective Image Content Analysis: Two Decades Review and New Perspectives	196
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	196
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting	193
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	190
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition	189
Deep Long-Tailed Learning: A Survey	183
Simplicial Complex Neural Networks	180
Prior Image Guided Snapshot Compressive Spectral Imaging	178

Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting	178
Fast Component Tree Computation for Images of Limited Levels	177
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation	177
Human-Centric Transformer for Domain Adaptive Action Recognition	176
Cover	175
Cover 2	174
Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation	174
Cover	173
Cover	170
Table of Contents	168
IEEE Computer Society Has You Covered!	167
Differentially Private Graph Neural Networks for Whole-Graph Classification	167
TPAMI Information for Authors	166
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning	164
Point Set Registration for 3D Range Scans Using Fuzzy Cluster-Based Metric and Efficient Global Optimization	164
VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision	162
Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition	161
Differential Viewpoints for Ground Terrain Material Recognition	156
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets	156
A Variational EM Acceleration for Efficient Clustering at Very Large Scales	155
Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification	154
Compositional Scene Representation Learning via Reconstruction: A Survey	154
Unbiased Scene Graph Generation via Two-Stage Causal Modeling	153
Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey	152
BNET: Batch Normalization With Enhanced Linear Transformation	151
MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network	151
Image Lens Flare Removal Using Adversarial Curve Learning	150
Knowledge-Based Embodied Question Answering	149
On the Robustness of Average Losses for Partial-Label Learning	147
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks	147
Spatial-Temporal Transformer for Video Snapshot Compressive Imaging	140
Image-to-Image Translation With Disentangled Latent Vectors for Face Editing	139
Orientational Distribution Learning with Hierarchical Spatial Attention for Open Set Recognition	139
Learning to See Through With Events	138
LMP-GAN: Out-Of-Distribution Detection For Non-Control Data Malware Attacks	137
Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification	136
Rate-Distortion Theory in Coding for Machines and its Applications	136
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning	134
Correcting Optical Aberration via Depth-Aware Point Spread Functions	133
SPLiT: Single Portrait Lighting Estimation via a Tetrad of Face Intrinsics	132
Dynamic Self-Supervised Teacher-Student Network Learning	131
Learning Graph Attentions via Replicator Dynamics	129
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos	129
Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes for Pruning is Possible Without Retraining	127
Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation	125
GradMDM: Adversarial Attack on Dynamic Networks	125
Human Interaction Understanding With Consistency-Aware Learning	125
Revisiting Nonlocal Self-Similarity from Continuous Representation	125
Discriminant Feature Extraction by Generalized Difference Subspace	124