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 2021-11-01 to 2025-11-01.)

Article	Citations
Consensus Sparsity: Multi-Context Sparse Image Representation via L _∞-Induced Matrix Variate	684
SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes With Cross-Object Consistency	654
HAda: Hyper-Adaptive Parameter-Efficient Learning for Multi-View ConvNets	592
Pro2Diff: Proposal Propagation for Multi-Object Tracking via the Diffusion Model	581
Multiframe Joint Enhancement for Early Interlaced Videos	482
Fine-Grained Recognition With Learnable Semantic Data Augmentation	434
Cross-Modality Pyramid Alignment for Visual Intention Understanding	402
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments	397
MaCon: A Generic Self-Supervised Framework for Unsupervised Multimodal Change Detection	363
An Adaptive Multi-Granularity Graph Representation of Image via Granular-ball Computing	361
Uncertainty-Guided Refinement for Fine-Grained Salient Object Detection	286
Discrete Metric Learning for Fast Image Set Classification	282
Bi-Nuclear Tensor Schatten-p Norm Minimization for Multi-View Subspace Clustering	253
GMLight: Lighting Estimation via Geometric Distribution Approximation	234
Graph Convolutional Dictionary Selection With L₂_, ₚ Norm for Video Summarization	229
Cross-Modal Retrieval With Noisy Correspondence via Consistency Refining and Mining	211
Density-Guided Incremental Dominant Instance Exploration for Two-View Geometric Model Fitting	204
TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation	203
Multi-Granularity Contrastive Cross-Modal Collaborative Generation for End-to-End Long-Term Video Question Answering	199
Contrast-Reconstruction Representation Learning for Self-Supervised Skeleton-Based Action Recognition	197
Multimodal Unrolled Robust PCA for Background Foreground Separation	192
A Fast and Efficient Shape Blending by Stable and Analytically Invertible Finite Descriptors	192
Variational Structured Attention Networks for Deep Visual Representation Learning	189
A Low-Rank Tensor Decomposition Model With Factors Prior and Total Variation for Impulsive Noise Removal	178
Equivariant Local Reference Frames With Optimization for Robust Non-Rigid Point Cloud Correspondence	178

Automatic Quaternion-Domain Color Image Stitching	178
FF-LPD: A Real-Time Frame-by-Frame License Plate Detector With Knowledge Distillation and Feature Propagation	175
STPNet: Scale-Aware Text Prompt Network for Medical Image Segmentation	173
Self-Supervised Matting-Specific Portrait Enhancement and Generation	168
Color Spike Camera Reconstruction via Long Short-Term Temporal Aggregation of Spike Signals	163
AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation	162
Spatial Frequency Modulation Network for Efficient Image Dehazing	160
Canonical Correlation Analysis With Low-Rank Learning for Image Representation	158
Learning Spectral Cues for Multispectral and Panchromatic Image Fusion	145
An Explanation Method Based on Interpretable Linear Model With Four Key Characteristics	143
Real Image Denoising With a Locally-Adaptive Bitonic Filter	140
One-Class Classification Using ℓp-Norm Multiple Kernel Fisher Null Approach	140
Dual Alternating Direction Method of Multipliers for Inverse Imaging	139
Pose-Appearance Relational Modeling for Video Action Recognition	132
Harnessing Multi-modal Large Language Models for Measuring and Interpreting Color Differences	132
Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments	130
Attentive WaveBlock: Complementarity-Enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-Identification and Beyond	130
Cross-Domain Few-Shot Medical Image Segmentation via Dynamic Semantic Matching	129
Toward Efficient Test Time Adaptation With Hierarchical Distribution Alignment	129
Multi-Constraint Adversarial Networks for Unsupervised Image-to-Image Translation	129
Toward Projected Clustering With Aggregated Mapping	127
Few-Shot Learning With Class-Covariance Metric for Hyperspectral Image Classification	126
Graph Embedding Contrastive Multi-Modal Representation Learning for Clustering	126
Differentiable SAR Renderer and Image-Based Target Reconstruction	124
Attention-Guided Neural Networks for Full-Reference and No-Reference Audio-Visual Quality Assessment	121
Variational Bayes Image Restoration With Compressive Autoencoders	121
NeuralDiffuser: Neuroscience-Inspired Diffusion Guidance for fMRI Visual Reconstruction	120
Advances in Predictive RAHT for Geometric Point Cloud Compression	120
Non-Cascaded and Crosstalk-Free Multi-Image Encryption Based on Optical Scanning Holography Using 2D Orthogonal Compressive Sensing	120
Interactive Face Video Coding: A Generative Compression Framework	119
Cross-Domain Diffusion With Progressive Alignment for Efficient Adaptive Retrieval	117
Fast 3D Room Layout Estimation Based on Compact High-Level Representation	117
Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning	116
Grammar-Induced Wavelet Network for Human Parsing	114
Cross-Layer Contrastive Learning of Latent Semantics for Facial Expression Recognition	110
Motion and Appearance Decoupling Representation for Event Cameras	110
Unsupervised Modality-Transferable Video Highlight Detection With Representation Activation Sequence Learning	106
Hyperspectral Meets Optical Flow: Spectral Flow Extraction for Hyperspectral Image Classification	106
IMU-Assisted Online Video Background Identification	105
Efficient Semi-Supervised Multimodal Hashing With Importance Differentiation Regression	105
Transition Is a Process: Pair-to-Video Change Detection Networks for Very High Resolution Remote Sensing Images	104
Optimization-Inspired Learning With Architecture Augmentations and Control Mechanisms for Low-Level Vision	104
Inverse Image Frequency for Long-Tailed Image Recognition	103
Boundary-Aware Prototype in Semi-Supervised Medical Image Segmentation	102
SRS: Siamese Reconstruction-Segmentation Network Based on Dynamic-Parameter Convolution	99
Distractor-Aware Event-Based Tracking	99
Learning Dynamic Prompts for All-in-One Image Restoration	97
Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain	96
Precise Facial Landmark Detection by Reference Heatmap Transformer	95
KSS-ICP: Point Cloud Registration Based on Kendall Shape Space	93

SharpFormer: Learning Local Feature Preserving Global Representations for Image Deblurring	92
Stacked Deconvolutional Network for Semantic Segmentation	92
SegHSI: Semantic Segmentation of Hyperspectral Images With Limited Labeled Pixels	90
Video Moment Retrieval With Cross-Modal Neural Architecture Search	90
Toward Video Anomaly Retrieval From Video Anomaly Detection: New Benchmarks and Model	89
Addressing Challenges of Incorporating Appearance Cues Into Heuristic Multi-Object Tracker via a Novel Feature Paradigm	89
Decoupled Cross-Modal Phrase-Attention Network for Image-Sentence Matching	89
Cyclic Self-Training With Proposal Weight Modulation for Cross-Supervised Object Detection	88
Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction	88
Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion	88
Rethinking Sampling Strategies for Unsupervised Person Re-Identification	86