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 2021-12-01 to 2025-12-01.)

Article	Citations
[Back cover - Table of contents, continued]	3052
Front Cover	1641
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference	1575
Learn to Predict Sets Using Feed-Forward Neural Networks	1545
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	1497
Editorial: Introduction to the Special Section on Best of CVPR'2022	1483
Self-Supervised Skeleton Representation Learning Via Actionlet Contrast and Reconstruct	1160
BiBBDM: Bidirectional Image Translation With Brownian Bridge Diffusion Models	1135
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	955
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	772
Multi-Dataset, Multitask Learning of Egocentric Vision Tasks	727
MECD+ : Unlocking Event-Level Causal Graph Discovery for Video Reasoning	625
Face Forgery Detection by 3D Decomposition and Composition Search	583
ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks	575
Active Supervised Cross-Modal Retrieval	563
DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus	555
Event-Based Photometric Bundle Adjustment	534
On the Trade-Off Between Flatness and Optimization in Distributed Learning	509
VATr++: Choose Your Words Wisely for Handwritten Text Generation	504
Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective	496
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration	475
Learning to Guide a Saturation-Based Theorem Prover	472
Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting	461
Towards Accurate and Compact Architectures via Neural Architecture Transformer	460
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation	456

Prior Image Guided Snapshot Compressive Spectral Imaging	447
A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization	445
Enhancing Representations Through Heterogeneous Self-Supervised Learning	441
Quadratic Matrix Factorization With Applications to Manifold Learning	426
Invariant Policy Learning: A Causal Perspective	411
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	405
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	403
A Generative Model for Generic Light Field Reconstruction	403
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification	401
Towards Unified Deep Image Deraining: A Survey and a New Benchmark	390
SNI-SLAM++: Tightly-Coupled Semantic Neural Implicit SLAM	378
Unsupervised Domain Adaptation via Discriminative Manifold Propagation	362
A Clustering Validity Index With Multi-Granularity Fusion for Multiple Fuzzy Clustering Algorithms	361
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition	359
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning	358
Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution	354
Point-to-Pixel Prompting for Point Cloud Analysis With Pre-Trained Image Models	352
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	349
Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data	339
Implicit Annealing in Kernel Spaces: A Strongly Consistent Clustering Approach	338
Video Demoireing Using Focused-Defocused Dual-Camera System	334
Physics-Informed Guided Disentanglement in Generative Networks	333
Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures	321
Interactive NeRF Geometry Editing With Shape Priors	318
Instance Shadow Detection with A Single-Stage Detector	318
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	315
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	313
Modeling Noisy Annotations for Point-Wise Supervision	310
Centerless Clustering	285
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	283
Rethinking Rotation-Invariant Recognition of Fine-grained Shapes from the Perspective of Contour Points	269
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	266
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing	261
Inferring Point Cloud Quality via Graph Similarity	258
Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching	257
Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes	257
Locating and Counting Heads in Crowds With a Depth Prior	252
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting	247
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	245
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search	243
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks	242
Simplicial Complex Neural Networks	242
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	236
Are Graph Convolutional Networks With Random Weights Feasible?	234
Deep Non-Rigid Structure From Motion With Missing Data	230
Learning Graph Convolutional Networks for Multi-Label Recognition and Applications	229
Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method	229
Transformer-Based Visual Segmentation: A Survey	225
Face Generation and Editing With StyleGAN: A Survey	224
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	223

Affective Image Content Analysis: Two Decades Review and New Perspectives	222
Graph Convolutional Module for Temporal Action Localization in Videos	216
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	215
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	215
Structure-Preserving Image Super-Resolution	213
Deep Long-Tailed Learning: A Survey	209
IEEE Computer Society Has You Covered!	209
Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification	209
Cover 2	208
Fast Component Tree Computation for Images of Limited Levels	207
BNET: Batch Normalization With Enhanced Linear Transformation	205
Universal Image Segmentation With Efficiency	204
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration	201
Temporal Feature Matters: A Framework for Diffusion Model Quantization	201
M³D: a Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information Extraction	200
Spatial-Temporal Transformer for Video Snapshot Compressive Imaging	197
Learning to See Through With Events	196
Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights	195
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning	191
MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation	187
Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation	183
On Positive-Unlabeled Classification From Corrupted Data in GANs	183
Learning Graph Attentions via Replicator Dynamics	175
Correcting Optical Aberration via Depth-Aware Point Spread Functions	175
Image Lens Flare Removal Using Adversarial Curve Learning	174
Bridging Actions: Generate 3D Poses and Shapes In-Between Photos	174
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets	173
GenPoly: Learning Generalized and Tessellated Shape Priors via 3D Polymorphic Evolving	170
To Fold or Not to Fold: Graph Regularized Tensor Train for Visual Data Completion	170
Ensemble Multi-Quantiles: Adaptively Flexible Distribution Prediction for Uncertainty Quantification	167
SPLiT: Single Portrait Lighting Estimation via a Tetrad of Face Intrinsics	164
Learning Efficient Meshflow and Optical Flow from Event Cameras	164
Adaptive Transfer Kernel Learning for Transfer Gaussian Process Regression	164
Differential Viewpoints for Ground Terrain Material Recognition	164
Deep Learning-Based Point Cloud Compression: An In-Depth Survey and Benchmark	163
Reduced-Rank Tensor-on-Tensor Regression and Tensor-Variate Analysis of Variance	162
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning	161
A Variational EM Acceleration for Efficient Clustering at Very Large Scales	160
Human-Centric Transformer for Domain Adaptive Action Recognition	158
Inter-Intra Hypergraph Computation for Survival Prediction on Whole Slide Images	157
On the Robustness of Average Losses for Partial-Label Learning	152
SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration	149
InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis With Semantic Graph Prior	149
Power Normalizations in Fine-Grained Image, Few-Shot Image and Graph Classification	148
Out-of-Domain Generalization From a Single Source: An Uncertainty Quantification Approach	148
GradMDM: Adversarial Attack on Dynamic Networks	147
Human Interaction Understanding With Consistency-Aware Learning	147
Curriculum-Based Asymmetric Multi-Task Reinforcement Learning	147
Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition	146
Dynamic Self-Supervised Teacher-Student Network Learning	146
Variational Data-Free Knowledge Distillation for Continual Learning	146
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation	144
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks	143
LMP-GAN: Out-of-Distribution Detection for Non-Control Data Malware Attacks	141
Compositional Scene Representation Learning via Reconstruction: A Survey	141
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks	139
Enhancing Photorealism Enhancement	138
Learning From Partially Labeled Data for Multi-Organ and Tumor Segmentation	138
Unbiased Scene Graph Generation via Two-Stage Causal Modeling	135
Rate-Distortion Theory in Coding for Machines and Its Applications	134
Discriminant Feature Extraction by Generalized Difference Subspace	134