OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 109. 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 2021-02-01 to 2025-02-01.)

Article	Citations
[Front inside cover]	2260
IEEE Transactions on Pattern Analysis and Machine Intelligence Publication Information	1892
Depth Restoration in Under-Display Time-of-Flight Imaging	1537
Cover 2	1074
Cover 4 [Table of Contents, back cover]	1026
Front Cover	1019
Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distribution	994
Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling	987
IEEE Computer Society Information	925
Front Cover	908
Cover 3	868
Cover	794
Table of Contents	637
[Back inside cover]	585
Cover	575
Bilinear Image Translation for Temporal Analysis of Photo Collections	556
Editorial Board	486
Fully Sparse Fusion for 3D Object Detection	464
What Makes Deviant Places?	463
A Closed-Form, Pairwise Solution to Local Non-Rigid Structure-From-Motion	453
Asymmetric Convolution: An Efficient and Generalized Method to Fuse Feature Maps in Multiple Vision Tasks	396
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains	377
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models	371
Semi-Supervised Multi-View Deep Discriminant Representation Learning	359
Deep Learning Methods for Calibrated Photometric Stereo and Beyond	359

Physics-Informed Guided Disentanglement in Generative Networks	328
Learning to Augment Poses for 3D Human Pose Estimation in Images and Videos	314
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time	311
Learning by Seeing More Classes	298
A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image Analysis	296
RayMVSNet++: Learning Ray-Based 1D Implicit Fields for Accurate Multi-View Stereo	296
Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation	290
Generating Hypergraph-Based High-Order Representations of Whole-Slide Histopathological Images for Survival Prediction	282
EM-Driven Unsupervised Learning for Efficient Motion Segmentation	279
Deep Order-Preserving Learning With Adaptive Optimal Transport Distance	276
Structure-Preserving Image Super-Resolution	275
Geometry-Aware Generation of Adversarial Point Clouds	273
Holistic Prototype Activation for Few-Shot Segmentation	273
Fourier-Based and Rational Graph Filters for Spectral Processing	258
FeatAug-DETR: Enriching One-to-Many Matching for DETRs With Feature Augmentation	254
Towards a Deeper Understanding of Global Covariance Pooling in Deep Learning: An Optimization Perspective	249
Vicinity Vision Transformer	245
Deterministic Approximate Methods for Maximum Consensus Robust Fitting	236
Dual Instance-Consistent Network for Cross-Domain Object Detection	233
ZeroNAS: Differentiable Generative Adversarial Networks Search for Zero-Shot Learning	229
Centerless Clustering	220
SibNet: Sibling Convolutional Encoder for Video Captioning	219
Tensor Low-Rank Representation for Data Recovery and Clustering	215
Communication-Efficient Randomized Algorithm for Multi-Kernel Online Federated Learning	211
Logarithmic Schatten-p Norm Minimization for Tensorial Multi-view Subspace Clustering	209
A Generative Model for Generic Light Field Reconstruction	205
Object Affinity Learning: Towards Annotation-Free Instance Segmentation	202
Create Your World: Lifelong Text-to-Image Diffusion	202
Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation	201
On the Optimality of Sufficient Statistics-based Quantizers	199
IEEE Computer Society Information	189
Semi-Infinitely Constrained Markov Decision Processes and Provably Efficient Reinforcement Learning	186
Learning to Follow and Generate Instructions for Language-Capable Navigation	183
From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm	181
Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing	179
Principal Uncertainty Quantification With Spatial Correlation for Image Restoration Problems	178
Heterogeneous Multi-Party Learning With Data-Driven Network Sampling	178
Importance Weighted Structure Learning for Scene Graph Generation	169
A Stream Algebra for Performance Optimization of Large Scale Computer Vision Pipelines	167
Erratum to “Deep Back-Projection Networks for Single Image Super-Resolution”	167
Searching a High Performance Feature Extractor for Text Recognition Network	166
Graph Transformer GANs With Graph Masked Modeling for Architectural Layout Generation	164
B-Cos Alignment for Inherently Interpretable CNNs and Vision Transformers	161
Incomplete Gamma Kernels: Generalizing Locally Optimal Projection Operators	159
Semantic Probability Distribution Modeling for Diverse Semantic Image Synthesis	158
End-to-End Full Projector Compensation	157
Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method	156
GAN Compression: Efficient Architectures for Interactive Conditional GANs	154
Self-Supervised Arbitrary-Scale Implicit Point Clouds Upsampling	149
An Efficient Fisher Matrix Approximation Method for Large-Scale Neural Network Optimization	149

PWLU: Learning Specialized Activation Functions With the Piecewise Linear Unit	148
Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection	148
IEEE Transactions on Pattern Analysis and Machine Intelligence Publication Information	145
Semi-Dense Feature Matching With Transformers and its Applications in Multiple-View Geometry	141
How to Query an Oracle? Efficient Strategies to Label Data	140
Invariant Policy Learning: A Causal Perspective	140
Publications Seek 2023 Editors in Chief	139
State of the Journal Editorial	139
[Back cover - Table of contents, continued]	137
Unambiguous Text Localization, Retrieval, and Recognition for Cluttered Scenes	136
Understanding and Accelerating Neural Architecture Search With Training-Free and Theory-Grounded Metrics	135
Content-Aware Warping for View Synthesis	134
Point Cloud Instance Segmentation With Semi-Supervised Bounding-Box Mining	134
MNET++: Music-Driven Pluralistic Dancing Toward Multiple Dance Genre Synthesis	133
Unsupervised Learning of Graph Matching With Mixture of Modes via Discrepancy Minimization	131
Face Forgery Detection by 3D Decomposition and Composition Search	130
Optimization-Based Post-Training Quantization With Bit-Split and Stitching	130
NAAQA: A Neural Architecture for Acoustic Question Answering	129
Debiased Scene Graph Generation for Dual Imbalance Learning	127
MPS-NeRF: Generalizable 3D Human Rendering From Multiview Images	126
Deep Constraint-Based Propagation in Graph Neural Networks	126
Unsupervised Face Detection in the Dark	123
Global Instance Tracking: Locating Target More Like Humans	122
Context-Aware Graph Inference With Knowledge Distillation for Visual Dialog	121
DeepPhaseCut: Deep Relaxation in Phase for Unsupervised Fourier Phase Retrieval	121
Neural Prompt Search	119
PFENet++: Boosting Few-Shot Semantic Segmentation With the Noise-Filtered Context-Aware Prior Mask	116
Learning Bilateral Cost Volume for Rolling Shutter Temporal Super-Resolution	114
Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images	114
SODFormer: Streaming Object Detection With Transformer Using Events and Frames	112
Hunter: Exploring High-Order Consistency for Point Cloud Registration With Severe Outliers	112
Detecting and Grounding Multi-Modal Media Manipulation and Beyond	110
Neighbourhood Representative Sampling for Efficient End-to-End Video Quality Assessment	110
Relationship-Embedded Representation Learning for Grounding Referring Expressions	110
PLMP – Point-Line Minimal Problems in Complete Multi-View Visibility	109
Z-Splat: Z-Axis Gaussian Splatting for Camera-Sonar Fusion	109
An Asynchronous Linear Filter Architecture for Hybrid Event-Frame Cameras	109