OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Image Processing is 70. 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 2022-06-01 to 2026-06-01.)

Article	Citations
Variational Structured Attention Networks for Deep Visual Representation Learning	989
One-Class Classification Using ℓp-Norm Multiple Kernel Fisher Null Approach	907
TSFormer: Efficient Ultra-High-Definition Image Restoration via Trusted Min- p	838
An Explanation Method Based on Interpretable Linear Model With Four Key Characteristics	729
FF-LPD: A Real-Time Frame-by-Frame License Plate Detector With Knowledge Distillation and Feature Propagation	724
Density-Guided Incremental Dominant Instance Exploration for Two-View Geometric Model Fitting	587
Color Spike Camera Reconstruction via Long Short-Term Temporal Aggregation of Spike Signals	336
An Adaptive Multi-Granularity Graph Representation of Image via Granular-ball Computing	299
Toward Efficient Test Time Adaptation With Hierarchical Distribution Alignment	296
Equivariant Local Reference Frames With Optimization for Robust Non-Rigid Point Cloud Correspondence	289
Global Modeling Matters: A Fast, Lightweight, and Effective Baseline for Efficient Image Restoration	266
Toward Projected Clustering With Aggregated Mapping	254
LearnMat: Semantic-Aware Self-Supervision Fine-Grained Visual Recognition	242
COME: A Collaborative Optimization Framework With Low-Rank MoE for Indoor 3D Object Detection	204
Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation Learning	201
High-Fidelity Seismic Super-Resolution Using Prior-Informed Deep Learning With 3D Awareness	195
Zero-Pose-Prior NeRF: Recursive Radiance Field Reconstruction From Unposed and Unordered Images	190
TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation	188
Advancing Pre-Trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection	178
MaCon: A Generic Self-Supervised Framework for Unsupervised Multimodal Change Detection	177
LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models	174
HAda: Hyper-Adaptive Parameter-Efficient Learning for Multi-View ConvNets	174
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments	172
Consensus Sparsity: Multi-Context Sparse Image Representation via L _∞-Induced Matrix Variate	161
Revisiting Fine-Grained Image Analysis by Semantic-Part Alignment	159

Pro2Diff: Proposal Propagation for Multi-Object Tracking via the Diffusion Model	150
Graph Embedding Contrastive Multi-Modal Representation Learning for Clustering	147
Cross-Modal Retrieval With Noisy Correspondence via Consistency Refining and Mining	146
SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes With Cross-Object Consistency	141
Star-Shaped Multi-Person Interaction Graph Model for Group Skeleton-Based Action Recognition	129
Multi-Granularity Contrastive Cross-Modal Collaborative Generation for End-to-End Long-Term Video Question Answering	126
Bi-Nuclear Tensor Schatten-p Norm Minimization for Multi-View Subspace Clustering	118
Automatic Quaternion-Domain Color Image Stitching	116
AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation	110
Cross-Modality Pyramid Alignment for Visual Intention Understanding	109
Fine-Grained Recognition With Learnable Semantic Data Augmentation	108
Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments	105
Leveraging Feature Alignment in Grassmannian Manifold for Multi-output Regression Tasks	104
Spatial Frequency Modulation Network for Efficient Image Dehazing	103
Pose-Appearance Relational Modeling for Video Action Recognition	102
Harnessing Multi-Modal Large Language Models for Measuring and Interpreting Color Differences	101
Cross-Domain Few-Shot Medical Image Segmentation via Dynamic Semantic Matching	98
STPNet: Scale-Aware Text Prompt Network for Medical Image Segmentation	97
Focus on Finding Deepfakes: A Robust Proactive Detection Method Based on Orthogonal Moment Watermarking	96
Uncertainty-Guided Refinement for Fine-Grained Salient Object Detection	93
Attention-Guided Neural Networks for Full-Reference and No-Reference Audio-Visual Quality Assessment	92
Advances in Predictive RAHT for Geometric Point Cloud Compression	91
Inverse Image Frequency for Long-Tailed Image Recognition	90
Fast 3D Room Layout Estimation Based on Compact High-Level Representation	89
ASDTracker: Adaptively Sparse Detection With Attention-Guided Refinement for Efficient Multi-Object Tracking	87
Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning	84
Perceptually Weighted Rate Distortion Optimization for Video-Based Point Cloud Compression	83
Spatial-Temporal Scene Graph Generation for Open-Vocabulary Multiple Object Tracking	83
Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching	81
Toward Generalizable Forgery Detection and Reasoning	81
Addressing Challenges of Incorporating Appearance Cues Into Heuristic Multi-Object Tracker via a Novel Feature Paradigm	80
FD-SCU: Frequency Decomposition-Based Spectrum Collaborative Upsampling for Point Cloud Color Attribute	80
Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction	79
TSCCD: Temporal Self-Construction Cross-Domain Learning for Unsupervised Hyperspectral Change Detection	79
ScaleNet: Scaling up Pretrained Neural Networks With Incremental Parameters	79
Stacked Deconvolutional Network for Semantic Segmentation	77
Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs	77
Unsupervised Modality-Transferable Video Highlight Detection With Representation Activation Sequence Learning	77
Optimization-Inspired Learning With Architecture Augmentations and Control Mechanisms for Low-Level Vision	75
Decoupled Cross-Modal Phrase-Attention Network for Image-Sentence Matching	75
MicroSDF: Microfacet-Driven Hybrid Neural SDFs for Mixed-Reflectance Surface Reconstruction	73
NR-MVSNet: Learning Multi-View Stereo Based on Normal Consistency and Depth Refinement	73
Cross-Domain Diffusion With Progressive Alignment for Efficient Adaptive Retrieval	73
SRS: Siamese Reconstruction-Segmentation Network Based on Dynamic-Parameter Convolution	72
SharpFormer: Learning Local Feature Preserving Global Representations for Image Deblurring	72
Precise Facial Landmark Detection by Reference Heatmap Transformer	70
Soft Supervision Guided Spatial-Temporal Refinement Network For Video-based Visible-Infrared Person Re-Identification	70
Commonality Feature Representation Learning for Unsupervised Multimodal Change Detection	70
Fuzzy Sparse Subspace Clustering for Infrared Image Segmentation	70