OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Image Processing is 86. 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
Consensus Sparsity: Multi-Context Sparse Image Representation via L _∞-Induced Matrix Variate	717
Pro2Diff: Proposal Propagation for Multi-Object Tracking via the Diffusion Model	700
Harnessing Multi-modal Large Language Models for Measuring and Interpreting Color Differences	619
Dual Alternating Direction Method of Multipliers for Inverse Imaging	615
An Explanation Method Based on Interpretable Linear Model With Four Key Characteristics	502
Multiframe Joint Enhancement for Early Interlaced Videos	456
An Adaptive Multi-Granularity Graph Representation of Image via Granular-ball Computing	443
Graph Convolutional Dictionary Selection With L₂_, ₚ Norm for Video Summarization	409
Toward Efficient Test Time Adaptation With Hierarchical Distribution Alignment	402
Cross-Domain Few-Shot Medical Image Segmentation via Dynamic Semantic Matching	376
A Fast and Efficient Shape Blending by Stable and Analytically Invertible Finite Descriptors	301
Variational Structured Attention Networks for Deep Visual Representation Learning	293
Equivariant Local Reference Frames With Optimization for Robust Non-Rigid Point Cloud Correspondence	255
Self-Supervised Matting-Specific Portrait Enhancement and Generation	246
Color Spike Camera Reconstruction via Long Short-Term Temporal Aggregation of Spike Signals	244
Canonical Correlation Analysis With Low-Rank Learning for Image Representation	229
Learning Spectral Cues for Multispectral and Panchromatic Image Fusion	210
Multi-Constraint Adversarial Networks for Unsupervised Image-to-Image Translation	209
A Low-Rank Tensor Decomposition Model With Factors Prior and Total Variation for Impulsive Noise Removal	209
SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes With Cross-Object Consistency	205
Spatial Frequency Modulation Network for Efficient Image Dehazing	200
Pose-Appearance Relational Modeling for Video Action Recognition	195
MaCon: A Generic Self-Supervised Framework for Unsupervised Multimodal Change Detection	194
AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation	188
HAda: Hyper-Adaptive Parameter-Efficient Learning for Multi-View ConvNets	188

Discrete Metric Learning for Fast Image Set Classification	187
One-Class Classification Using ℓp-Norm Multiple Kernel Fisher Null Approach	186
TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation	175
FF-LPD: A Real-Time Frame-by-Frame License Plate Detector With Knowledge Distillation and Feature Propagation	174
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments	173
Automatic Quaternion-Domain Color Image Stitching	169
Fine-Grained Recognition With Learnable Semantic Data Augmentation	168
Cross-Modality Pyramid Alignment for Visual Intention Understanding	163
STPNet: Scale-Aware Text Prompt Network for Medical Image Segmentation	155
Multimodal Unrolled Robust PCA for Background Foreground Separation	154
Differentiable SAR Renderer and Image-Based Target Reconstruction	148
Attentive WaveBlock: Complementarity-Enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-Identification and Beyond	147
Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments	145
Real Image Denoising With a Locally-Adaptive Bitonic Filter	138
Contrast-Reconstruction Representation Learning for Self-Supervised Skeleton-Based Action Recognition	137
Uncertainty-Guided Refinement for Fine-Grained Salient Object Detection	136
Multi-Granularity Contrastive Cross-Modal Collaborative Generation for End-to-End Long-Term Video Question Answering	134
LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models	132
Cross-Modal Retrieval With Noisy Correspondence via Consistency Refining and Mining	132
Density-Guided Incremental Dominant Instance Exploration for Two-View Geometric Model Fitting	131
Few-Shot Learning With Class-Covariance Metric for Hyperspectral Image Classification	131
Graph Embedding Contrastive Multi-Modal Representation Learning for Clustering	129
GMLight: Lighting Estimation via Geometric Distribution Approximation	129
Toward Projected Clustering With Aggregated Mapping	128
Attention-Guided Neural Networks for Full-Reference and No-Reference Audio-Visual Quality Assessment	127
Bi-Nuclear Tensor Schatten-p Norm Minimization for Multi-View Subspace Clustering	127
Advances in Predictive RAHT for Geometric Point Cloud Compression	125
Interactive Face Video Coding: A Generative Compression Framework	124
NeuralDiffuser: Neuroscience-Inspired Diffusion Guidance for fMRI Visual Reconstruction	124
Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning	124
Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction	123
Unsupervised Modality-Transferable Video Highlight Detection With Representation Activation Sequence Learning	122
IMU-Assisted Online Video Background Identification	120
Distractor-Aware Event-Based Tracking	118
Bidirectional Mapping Coupled GAN for Generalized Zero-Shot Learning	117
Motion and Appearance Decoupling Representation for Event Cameras	117
SRS: Siamese Reconstruction-Segmentation Network Based on Dynamic-Parameter Convolution	112
Cyclic Self-Training With Proposal Weight Modulation for Cross-Supervised Object Detection	110
Learning Dynamic Prompts for All-in-One Image Restoration	109
ScaleNet: Scaling up Pretrained Neural Networks With Incremental Parameters	108
Coarse-to-Fine Contrastive Self-Supervised Feature Learning for Land-Cover Classification in SAR Images With Limited Labeled Data	108
Addressing Challenges of Incorporating Appearance Cues Into Heuristic Multi-Object Tracker via a Novel Feature Paradigm	108
Unsupervised Person Re-Identification With Stochastic Training Strategy	107
Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain	103
Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion	103
Commonality Feature Representation Learning for Unsupervised Multimodal Change Detection	102
Hyperspectral Meets Optical Flow: Spectral Flow Extraction for Hyperspectral Image Classification	101
Rethinking Sampling Strategies for Unsupervised Person Re-Identification	100
Perceptually Weighted Rate Distortion Optimization for Video-Based Point Cloud Compression	99
Grammar-Induced Wavelet Network for Human Parsing	98

DUT: Learning Video Stabilization by Simply Watching Unstable Videos	95
Boundary-Aware Prototype in Semi-Supervised Medical Image Segmentation	94
SharpFormer: Learning Local Feature Preserving Global Representations for Image Deblurring	92
Decoupled Cross-Modal Phrase-Attention Network for Image-Sentence Matching	92
FsaNet: Frequency Self-Attention for Semantic Segmentation	91
Multi-Exposure Image Fusion via Deformable Self-Attention	90
Stacked Deconvolutional Network for Semantic Segmentation	90
Cross-Attentional Spatio-Temporal Semantic Graph Networks for Video Question Answering	89
Point-Based Learnable Query Generator for Human–Object Interaction Detection	89
SegHSI: Semantic Segmentation of Hyperspectral Images With Limited Labeled Pixels	89
Fast 3D Room Layout Estimation Based on Compact High-Level Representation	88
Fuzzy Sparse Subspace Clustering for Infrared Image Segmentation	86