OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Image Processing is 69. 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 2022-05-01 to 2026-05-01.)

Article	Citations
Variational Structured Attention Networks for Deep Visual Representation Learning	952
One-Class Classification Using ℓp-Norm Multiple Kernel Fisher Null Approach	872
TSFormer: Efficient Ultra-High-Definition Image Restoration via Trusted Min- p	794
An Explanation Method Based on Interpretable Linear Model With Four Key Characteristics	693
FF-LPD: A Real-Time Frame-by-Frame License Plate Detector With Knowledge Distillation and Feature Propagation	689
Density-Guided Incremental Dominant Instance Exploration for Two-View Geometric Model Fitting	551
Color Spike Camera Reconstruction via Long Short-Term Temporal Aggregation of Spike Signals	317
Focus on Finding Deepfakes: A Robust Proactive Detection Method Based on Orthogonal Moment Watermarking	294
Cross-Domain Few-Shot Medical Image Segmentation via Dynamic Semantic Matching	291
An Adaptive Multi-Granularity Graph Representation of Image via Granular-ball Computing	279
Harnessing Multi-Modal Large Language Models for Measuring and Interpreting Color Differences	257
Toward Efficient Test Time Adaptation With Hierarchical Distribution Alignment	244
Pose-Appearance Relational Modeling for Video Action Recognition	235
Equivariant Local Reference Frames With Optimization for Robust Non-Rigid Point Cloud Correspondence	195
Global Modeling Matters: A Fast, Lightweight, and Effective Baseline for Efficient Image Restoration	191
Toward Projected Clustering With Aggregated Mapping	186
LearnMat: Semantic-Aware Self-Supervision Fine-Grained Visual Recognition	179
COME: A Collaborative Optimization Framework With Low-Rank MoE for Indoor 3D Object Detection	179
Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation Learning	172
Consensus Sparsity: Multi-Context Sparse Image Representation via L _∞-Induced Matrix Variate	171
HAda: Hyper-Adaptive Parameter-Efficient Learning for Multi-View ConvNets	171
Revisiting Fine-Grained Image Analysis by Semantic-Part Alignment	167
Graph Embedding Contrastive Multi-Modal Representation Learning for Clustering	164
High-Fidelity Seismic Super-Resolution Using Prior-Informed Deep Learning With 3D Awareness	154
Uncertainty-Guided Refinement for Fine-Grained Salient Object Detection	153

Zero-Pose-Prior NeRF: Recursive Radiance Field Reconstruction From Unposed and Unordered Images	148
SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes With Cross-Object Consistency	143
TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation	143
Bi-Nuclear Tensor Schatten-p Norm Minimization for Multi-View Subspace Clustering	139
Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection	126
Multi-Granularity Contrastive Cross-Modal Collaborative Generation for End-to-End Long-Term Video Question Answering	121
Attention-Guided Neural Networks for Full-Reference and No-Reference Audio-Visual Quality Assessment	114
Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments	114
Fine-Grained Recognition With Learnable Semantic Data Augmentation	106
Star-Shaped Multi-Person Interaction Graph Model for Group Skeleton-Based Action Recognition	104
Automatic Quaternion-Domain Color Image Stitching	101
Pro2Diff: Proposal Propagation for Multi-Object Tracking via the Diffusion Model	101
LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models	100
STPNet: Scale-Aware Text Prompt Network for Medical Image Segmentation	100
MaCon: A Generic Self-Supervised Framework for Unsupervised Multimodal Change Detection	100
AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation	98
Spatial Frequency Modulation Network for Efficient Image Dehazing	95
Cross-Modal Retrieval With Noisy Correspondence via Consistency Refining and Mining	94
Cross-Modality Pyramid Alignment for Visual Intention Understanding	93
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments	91
Advances in Predictive RAHT for Geometric Point Cloud Compression	87
Fast 3D Room Layout Estimation Based on Compact High-Level Representation	87
Inverse Image Frequency for Long-Tailed Image Recognition	87
ASDTracker: Adaptively Sparse Detection With Attention-Guided Refinement for Efficient Multi-Object Tracking	86
Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning	83
Decoupled Cross-Modal Phrase-Attention Network for Image-Sentence Matching	82
Unsupervised Modality-Transferable Video Highlight Detection With Representation Activation Sequence Learning	81
Precise Facial Landmark Detection by Reference Heatmap Transformer	79
Perceptually Weighted Rate Distortion Optimization for Video-Based Point Cloud Compression	78
Fuzzy Sparse Subspace Clustering for Infrared Image Segmentation	78
Spatial-Temporal Scene Graph Generation for Open-Vocabulary Multiple Object Tracking	78
Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching	77
Toward Generalizable Forgery Detection and Reasoning	77
Rethinking Sampling Strategies for Unsupervised Person Re-Identification	76
FD-SCU: Frequency Decomposition-Based Spectrum Collaborative Upsampling for Point Cloud Color Attribute	75
Addressing Challenges of Incorporating Appearance Cues Into Heuristic Multi-Object Tracker via a Novel Feature Paradigm	74
Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction	74
Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs	73
Boundary-Aware Prototype in Semi-Supervised Medical Image Segmentation	73
TSCCD: Temporal Self-Construction Cross-Domain Learning for Unsupervised Hyperspectral Change Detection	73
ScaleNet: Scaling up Pretrained Neural Networks With Incremental Parameters	73
Optimization-Inspired Learning With Architecture Augmentations and Control Mechanisms for Low-Level Vision	71
SRS: Siamese Reconstruction-Segmentation Network Based on Dynamic-Parameter Convolution	71
Point-Based Learnable Query Generator for Human–Object Interaction Detection	70
Stacked Deconvolutional Network for Semantic Segmentation	69
Hyperspectral Meets Optical Flow: Spectral Flow Extraction for Hyperspectral Image Classification	69
Distractor-Aware Event-Based Tracking	69