OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 125. 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 2021-08-01 to 2025-08-01.)

Article	Citations
Learn to Predict Sets Using Feed-Forward Neural Networks	2865
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus	2478
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification	1382
Modeling Noisy Annotations for Point-Wise Supervision	1361
Cover	1310
Editorial Board	1285
[Back cover - Table of contents, continued]	1241
Front Cover	1211
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	1202
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference	904
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing	851
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	783
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	662
Deep Non-Rigid Structure From Motion With Missing Data	659
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	577
Enhancing Representations Through Heterogeneous Self-Supervised Learning	577
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning	541
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search	494
Quadratic Matrix Factorization With Applications to Manifold Learning	472
A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization	469
Interactive NeRF Geometry Editing With Shape Priors	460
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	429
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	429
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	418
A Clustering Validity Index with Multi-Granularity Fusion for Multiple Fuzzy Clustering Algorithms	417

Instance Shadow Detection with A Single-Stage Detector	399
ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks	393
Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures	383
Graph Convolutional Module for Temporal Action Localization in Videos	378
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification	368
Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes	367
Event-based Photometric Bundle Adjustment	367
Prior Image Guided Snapshot Compressive Spectral Imaging	365
Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting	356
Towards Accurate and Compact Architectures via Neural Architecture Transformer	355
Invariant Policy Learning: A Causal Perspective	352
A Generative Model for Generic Light Field Reconstruction	345
Structure-Preserving Image Super-Resolution	342
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting	323
Affective Image Content Analysis: Two Decades Review and New Perspectives	313
Towards Unified Deep Image Deraining: A Survey and a New Benchmark	305
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	305
Centerless Clustering	300
Physics-Informed Guided Disentanglement in Generative Networks	297
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks	295
VATr++: Choose Your Words Wisely for Handwritten Text Generation	294
Locating and Counting Heads in Crowds With a Depth Prior	289
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	283
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models	282
Face Forgery Detection by 3D Decomposition and Composition Search	279
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach	277
Active Supervised Cross-Modal Retrieval	270
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	259
On the Trade-off between Flatness and Optimization in Distributed Learning	259
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks	258
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data	257
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	243
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	241
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration	236
Multi-Task Head Pose Estimation in-the-Wild	231
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	227
Transformer-Based Visual Segmentation: A Survey	227
Deep Long-Tailed Learning: A Survey	223
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	218
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	214
Face Generation and Editing With StyleGAN: A Survey	214
Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching	214
Are Graph Convolutional Networks With Random Weights Feasible?	211
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	210
Learning to Guide a Saturation-Based Theorem Prover	210
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	206
Unsupervised Domain Adaptation via Discriminative Manifold Propagation	198
Inferring Point Cloud Quality via Graph Similarity	197
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	197
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition	195

Simplicial Complex Neural Networks	192
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation	188
Fast Component Tree Computation for Images of Limited Levels	187
Human-Centric Transformer for Domain Adaptive Action Recognition	186
Cover	185
Cover 2	185
Cover	183
Cover	179
Table of Contents	179
IEEE Computer Society Has You Covered!	177
TPAMI Information for Authors	176
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning	176
Point Set Registration for 3D Range Scans Using Fuzzy Cluster-Based Metric and Efficient Global Optimization	176
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets	175
A Variational EM Acceleration for Efficient Clustering at Very Large Scales	174
Image Lens Flare Removal Using Adversarial Curve Learning	173
MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network	173
Discriminant Feature Extraction by Generalized Difference Subspace	171
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation	169
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation	167
Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation	167
LMP-GAN: Out-of-Distribution Detection for Non-Control Data Malware Attacks	166
Universal Image Segmentation with Efficiency	165
Image-to-Image Translation With Disentangled Latent Vectors for Face Editing	164
Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes for Pruning is Possible Without Retraining	163
Accurate and Efficient Stereo Matching via Attention Concatenation Volume	160
On Positive-Unlabeled Classification From Corrupted Data in GANs	158
Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey	157
Hypergraph-Based Multi-View Action Recognition Using Event Cameras	154
Out-of-Domain Generalization From a Single Source: An Uncertainty Quantification Approach	153
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks	152
Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification	151
Temporal Feature Matters: A Framework for Diffusion Model Quantization	150
Power Normalizations in Fine-Grained Image, Few-Shot Image and Graph Classification	149
Dynamic Self-Supervised Teacher-Student Network Learning	144
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos	143
Learning Graph Attentions via Replicator Dynamics	142
Reduced-Rank Tensor-on-Tensor Regression and Tensor-Variate Analysis of Variance	140
Adaptive Transfer Kernel Learning for Transfer Gaussian Process Regression	136
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration	136
Curriculum-Based Asymmetric Multi-Task Reinforcement Learning	135
Differentially Private Graph Neural Networks for Whole-Graph Classification	133
BNET: Batch Normalization With Enhanced Linear Transformation	132
Inter-Intra Hypergraph Computation for Survival Prediction on Whole Slide Images	131
VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision	129
Revisiting Nonlocal Self-Similarity from Continuous Representation	129
HiGCIN: Hierarchical Graph-Based Cross Inference Network for Group Activity Recognition	128
Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification	127
On the Robustness of Average Losses for Partial-Label Learning	127
Correcting Optical Aberration via Depth-Aware Point Spread Functions	126
Asymmetric Loss Functions for Noise-Tolerant Learning: Theory and Applications	125