OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Image Processing is 71. 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
ADStereo: Efficient Stereo Matching With Adaptive Downsampling and Disparity Alignment	441
Reserve to Adapt: Mining Inter-Class Relations for Open-Set Domain Adaptation	428
Who, What, and Where: Composite-Semantics Instance Search for Story Videos	420
MaCon: A Generic Self-Supervised Framework for Unsupervised Multimodal Change Detection	354
Optimal Graph Learning-Based Label Propagation for Cross-Domain Image Classification	319
Deep Face Leakage: Inverting High-Quality Faces From Gradients Using Residual Optimization	285
MoVis: When 3D Object Detection is Like Human Monocular Vision	250
MaeFuse: Transferring Omni Features With Pretrained Masked Autoencoders for Infrared and Visible Image Fusion via Guided Training	250
Co-Learning Meets Stitch-Up for Noisy Multi-Label Visual Recognition	204
Scalable Face Image Coding via StyleGAN Prior: Toward Compression for Human-Machine Collaborative Vision	203
A General Dynamic Knowledge Distillation Method for Visual Analytics	190
Consensus Sparsity: Multi-Context Sparse Image Representation via L _∞-Induced Matrix Variate	190
Deep Hypersphere Feature Regularization for Weakly Supervised RGB-D Salient Object Detection	177
Cross-Modality Pyramid Alignment for Visual Intention Understanding	155
Attention-Guided Neural Networks for Full-Reference and No-Reference Audio-Visual Quality Assessment	148
6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-Based Instance Representation Learning	146
Multiple Information Prompt Learning for Cloth-Changing Person Re-Identification	145
Exploiting Latent Properties to Optimize Neural Codecs	144
Momentum Contrastive Teacher for Semi-Supervised Skeleton Action Recognition	143
Constrained Visual Representation Learning With Bisimulation Metrics for Safe Reinforcement Learning	134
Variational Structured Attention Networks for Deep Visual Representation Learning	133
IEEE Transactions on Image Processing Publication Information	133
Concept-Aware Video Captioning: Describing Videos With Effective Prior Information	127
Tensor Cascaded-Rank Minimization in Subspace: A Unified Regime for Hyperspectral Image Low-Level Vision	124
Unsupervised Meta Learning With Multiview Constraints for Hyperspectral Image Small Sample set Classification	124

Wavelet-Guided Promotion-Suppression Transformer for Surface-Defect Detection	122
Temporal Fusion: Continuous-Time Light Field Video Factorization	118
Adaptive Bit Selection for Scalable Deep Hashing	117
Harnessing Multi-modal Large Language Models for Measuring and Interpreting Color Differences	113
Spiking Neural Networks With Adaptive Membrane Time Constant for Event-Based Tracking	113
Super-Resolution Phase Retrieval Network for Single-Pattern Structured Light 3D Imaging	112
Dual-View Curricular Optimal Transport for Cross-Lingual Cross-Modal Retrieval	106
Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions	105
Equivariant Local Reference Frames with Optimization for Robust Non-rigid Point Cloud Correspondence	105
SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes With Cross-Object Consistency	102
UMCGL: Universal Multi-View Consensus Graph Learning With Consistency and Diversity	100
Multi-Label Adversarial Attack With New Measures and Self-Paced Constraint Weighting	99
An Embeddable Implicit IUVD Representation for Part-Based 3D Human Surface Reconstruction	98
CPI-Parser: Integrating Causal Properties Into Multiple Human Parsing	97
SWFormer: Stochastic Windows Convolutional Transformer for Hybrid Modality Hyperspectral Classification	97
Rethinking Noise Sampling in Class-Imbalanced Diffusion Models	96
Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation	93
To Boost Zero-Shot Generalization for Embodied Reasoning With Vision-Language Pre-Training	92
Segmentation-Free Velocity Field Super-Resolution on 4D Flow MRI	91
Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification	91
Exploring Multi-Modal Spatial–Temporal Contexts for High-Performance RGB-T Tracking	90
Unfolded Proximal Neural Networks for Robust Image Gaussian Denoising	89
Explainability Enhanced Object Detection Transformer With Feature Disentanglement	89
Learning Weak Semantics by Feature Graph for Attribute-Based Person Search	87
CWSCNet: Channel-Weighted Skip Connection Network for Underwater Object Detection	87
Learning-Based Rate Control for Video-Based Point Cloud Compression	86
A Novel Hybrid Level Set Model for Non-Rigid Object Contour Tracking	85
GMLight: Lighting Estimation via Geometric Distribution Approximation	85
Frequency Information Disentanglement Network for Video-Based Person Re-Identification	84
Prototype Adaption and Projection for Few- and Zero-Shot 3D Point Cloud Semantic Segmentation	83
Dynamic Neural Network for Lossy-to-Lossless Image Coding	83
Geometry-Aware Deep Video Deblurring via Recurrent Feature Refinement	81
Fine-Grained Video Retrieval With Scene Sketches	80
Local Orthogonal Moments for Local Features	80
Dual Alternating Direction Method of Multipliers for Inverse Imaging	79
JigsawGAN: Auxiliary Learning for Solving Jigsaw Puzzles With Generative Adversarial Networks	79
Rebalanced Zero-Shot Learning	78
Multi-Constraint Adversarial Networks for Unsupervised Image-to-Image Translation	77
Multisubject Task-Related fMRI Data Processing via a Two-Stage Generalized Canonical Correlation Analysis	77
Revisiting the Regularizers in Blind Image Deblurring With a New One	76
User-Guided Deep Human Image Matting Using Arbitrary Trimaps	75
Tree-Structured Data Clustering-Driven Neural Network for Intra Prediction in Video Coding	73
Exploring the Robustness of Human Parsers Toward Common Corruptions	73
CalibNet: Dual-Branch Cross-Modal Calibration for RGB-D Salient Instance Segmentation	72
A Low-Rank Tensor Decomposition Model With Factors Prior and Total Variation for Impulsive Noise Removal	72
Sparse Coding Inspired LSTM and Self-Attention Integration for Medical Image Segmentation	71