OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Pattern Analysis and Machine Intelligence is 121. 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 2021-04-01 to 2025-04-01.)

Article	Citations
[Front inside cover]	2531
IEEE Transactions on Pattern Analysis and Machine Intelligence Publication Information	1942
Cover 2	1248
Cover 4 [Table of Contents, back cover]	1175
Front Cover	1163
Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distribution	1121
Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling	1086
IEEE Computer Society Information	1080
Front Cover	1005
Cover 3	999
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting	994
Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline	784
Diffusion Models in Low-Level Vision: A Survey	651
Table of Contents	633
[Back inside cover]	603
Cover	590
Editorial Board	573
Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction	548
Learning the Optimal Discriminant SVM With Feature Extraction	526
Instruction-Guided Scene Text Recognition	473
Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines	455
Quantum Gated Recurrent Neural Networks	413
One-for-All: Towards Universal Domain Translation With a Single StyleGAN	400
Glissando-Net: Deep Single View Category Level Pose Estimation and 3D Reconstruction	394
DHVT: Dynamic Hybrid Vision Transformer for Small Dataset Recognition	388

Behind Every Domain There is a Shift: Adapting Distortion-Aware Vision Transformers for Panoramic Semantic Segmentation	387
AD-VAT+: An Asymmetric Dueling Mechanism for Learning and Understanding Visual Active Tracking	387
Video Coding for Machines: Compact Visual Representation Compression for Intelligent Collaborative Analytics	356
Old Photo Restoration via Deep Latent Space Translation	348
Decoding Brain Representations by Multimodal Learning of Neural Activity and Visual Features	340
Exploiting Wavelength Diversity for High Resolution Time-of-Flight 3D Imaging	337
A Lightweight Optical Flow CNN —Revisiting Data Fidelity and Regularization	336
SIFT Matching by Context Exposed	330
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation	324
Learning Invariance From Generated Variance for Unsupervised Person Re-Identification	319
Sparse R-CNN: An End-to-End Framework for Object Detection	313
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness	305
Consistent 3D Hand Reconstruction in Video via Self-Supervised Learning	301
Normalization Techniques in Training DNNs: Methodology, Analysis and Application	299
Deep Long-Tailed Learning: A Survey	296
An Integrated Fast Hough Transform for Multidimensional Data	292
Lazily Aggregated Quantized Gradient Innovation for Communication-Efficient Federated Learning	291
Joint Feature Synthesis and Embedding: Adversarial Cross-Modal Retrieval Revisited	278
On the Optimality of Sufficient Statistics-based Quantizers	275
IEEE Computer Society Information	274
A Causal Adjustment Module for Debiasing Scene Graph Generation	273
Quasi-Metric Learning for Bilateral Person-Job Fit	270
Global Model Selection via Solution Paths for Robust Support Vector Machine	268
Remembering What is Important: A Factorised Multi-Head Retrieval and Auxiliary Memory Stabilisation Scheme for Human Motion Prediction	267
IEEE Transactions on Pattern Analysis and Machine Intelligence Publication Information	266
DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation	262
Multiview Unsupervised Shapelet Learning for Multivariate Time Series Clustering	261
DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation	260
PyMAF-X: Towards Well-Aligned Full-Body Model Regression From Monocular Images	252
Learning an Invariant and Equivariant Network for Weakly Supervised Object Detection	247
Continual Image Deraining With Hypergraph Convolutional Networks	244
Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering	239
A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image Analysis	238
Instance Shadow Detection with A Single-Stage Detector	231
On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective	218
Adaptive Region-Specific Loss for Improved Medical Image Segmentation	214
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation	209
Transformer-Based Visual Segmentation: A Survey	209
UniMiSS+: Universal Medical Self-Supervised Learning From Cross-Dimensional Unpaired Data	206
Robust Multi-View Clustering With Incomplete Information	202
PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-Step Point Moving Paths	196
Wavelet Approximation-Aware Residual Network for Single Image Deraining	194
CAS(ME)<sup>3</sup>: A Third Generation Facial Spontaneous Micro-Expression Database with Depth Information and High Ecological Validity	192
Unsupervised Grouped Axial Data Modeling via Hierarchical Bayesian Nonparametric Models With Watson Distributions	187
BadLabel: A Robust Perspective on Evaluating and Enhancing Label-Noise Learning	184
Deep Learning Methods for Calibrated Photometric Stereo and Beyond	184
Fully Sparse Fusion for 3D Object Detection	182
DVIS++: Improved Decoupled Framework for Universal Video Segmentation	178
Systematic Bias of Machine Learning Regression Models and Correction	177
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	174

Impact of Noisy Supervision in Foundation Model Learning	174
Publications Seek 2023 Editors in Chief	172
[Back cover - Table of contents, continued]	172
Cover	169
[Back cover]	167
Cover	166
Cover	165
Table of Contents	163
IEEE Quantum Week	161
Front Cover	161
Cover 4 [Table of Contents]	160
Cover 2	159
Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning	158
Locating and Counting Heads in Crowds With a Depth Prior	157
Learning to Follow and Generate Instructions for Language-Capable Navigation	157
Fast and Informative Model Selection Using Learning Curve Cross-Validation	156
Detecting Line Segments in Motion-Blurred Images With Events	155
Extraction of an Explanatory Graph to Interpret a CNN	154
From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm	154
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation	153
Continuous-Time Object Segmentation Using High Temporal Resolution Event Camera	152
Learning Without Forgetting for Vision-Language Models	151
Intelligent Bionic Polarization Orientation Method Using Biological Neuron Model for Harsh Conditions	151
Equivariant Diffusion Model with A5-Group Neurons for Joint Pose Estimation and Shape Reconstruction	151
Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion	151
MB-RACS: Measurement-Bounds-based Rate-Adaptive Image Compressed Sensing Network	147
BEVHeight++: Toward Robust Visual Centric 3D Object Detection	146
Active Supervised Cross-Modal Retrieval	145
Fourier-Based and Rational Graph Filters for Spectral Processing	141
Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation	140
SimSwap++: Towards Faster and High-Quality Identity Swapping	140
Towards Accurate and Compact Architectures via Neural Architecture Transformer	139
RayMVSNet++: Learning Ray-Based 1D Implicit Fields for Accurate Multi-View Stereo	138
Hunter: Exploring High-Order Consistency for Point Cloud Registration With Severe Outliers	137
Multi-Task Head Pose Estimation in-the-Wild	136
Context Disentangling and Prototype Inheriting for Robust Visual Grounding	131
One-Hot Graph Encoder Embedding	130
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning	130
SibNet: Sibling Convolutional Encoder for Video Captioning	128
Incomplete Label Multiple Instance Multiple Label Learning	128
Towards Age-Invariant Face Recognition	127
DSGN++: Exploiting Visual-Spatial Relation for Stereo-Based 3D Detectors	126
PLMP – Point-Line Minimal Problems in Complete Multi-View Visibility	125
Simple Primitives With Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-Shot Learning	122
On Exploring Multiplicity of Primitives and Attributes for Texture Recognition in the Wild	122
Booster: A Benchmark for Depth From Images of Specular and Transparent Surfaces	122
Boosting Photon-Efficient Image Reconstruction with A Unified Deep Neural Network	121