OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Image Processing is 76. 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 2022-08-01 to 2026-08-01.)

Article	Citations
Variational Structured Attention Networks for Deep Visual Representation Learning	1091
TSFormer: Efficient Ultra-High-Definition Image Restoration via Trusted Min- p	995
An Explanation Method Based on Interpretable Linear Model With Four Key Characteristics	923
Density-Guided Incremental Dominant Instance Exploration for Two-View Geometric Model Fitting	830
Color Spike Camera Reconstruction via Long Short-Term Temporal Aggregation of Spike Signals	810
Equivariant Local Reference Frames With Optimization for Robust Non-Rigid Point Cloud Correspondence	646
Star-Shaped Multi-Person Interaction Graph Model for Group Skeleton-Based Action Recognition	382
Bi-Nuclear Tensor Schatten-p Norm Minimization for Multi-View Subspace Clustering	324
AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation	321
Cross-Modality Pyramid Alignment for Visual Intention Understanding	313
COME: A Collaborative Optimization Framework With Low-Rank MoE for Indoor 3D Object Detection	295
High-Fidelity Seismic Super-Resolution Using Prior-Informed Deep Learning With 3D Awareness	292
Zero-Pose-Prior NeRF: Recursive Radiance Field Reconstruction From Unposed and Unordered Images	275
Advancing Pre-Trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection	240
Consensus Sparsity: Multi-Context Sparse Image Representation via L _∞-Induced Matrix Variate	220
SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes With Cross-Object Consistency	219
Leveraging Feature Alignment in Grassmannian Manifold for Multi-Output Regression Tasks	212
One-Class Classification Using ℓp-Norm Multiple Kernel Fisher Null Approach	211
Cross-Domain Few-Shot Medical Image Segmentation via Dynamic Semantic Matching	205
Pro2Diff: Proposal Propagation for Multi-Object Tracking via the Diffusion Model	201
Pose-Appearance Relational Modeling for Video Action Recognition	197
Uncertainty-Guided Refinement for Fine-Grained Salient Object Detection	182
Spatial Frequency Modulation Network for Efficient Image Dehazing	180
Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation Learning	167
Toward Efficient Test Time Adaptation With Hierarchical Distribution Alignment	164

MaCon: A Generic Self-Supervised Framework for Unsupervised Multimodal Change Detection	155
FF-LPD: A Real-Time Frame-by-Frame License Plate Detector With Knowledge Distillation and Feature Propagation	154
TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation	153
Spectral State Fusion Tree Mamba for Hyperspectral Image Classification	151
Language Supervised Multi-Camera Multi-Object Tracking	148
Global Modeling Matters: A Fast, Lightweight, and Effective Baseline for Efficient Image Restoration	144
An Adaptive Multi-Granularity Graph Representation of Image via Granular-ball Computing	128
Toward Projected Clustering With Aggregated Mapping	124
Cross-Modal Retrieval With Noisy Correspondence via Consistency Refining and Mining	123
Focus on Finding Deepfakes: A Robust Proactive Detection Method Based on Orthogonal Moment Watermarking	118
LearnMat: Semantic-Aware Self-Supervision Fine-Grained Visual Recognition	117
Revisiting Fine-Grained Image Analysis by Semantic-Part Alignment	114
H ³ Former: Hypergraph-Based Semantic-Aware Aggregation via Hyperbolic Hierarchical Contrastive Loss for Fine-Grained Visual Classification	113
Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments	112
In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis From Language Models to Physics	106
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments	105
STPNet: Scale-Aware Text Prompt Network for Medical Image Segmentation	105
Graph Embedding Contrastive Multi-Modal Representation Learning for Clustering	104
Automatic Quaternion-Domain Color Image Stitching	103
HAda: Hyper-Adaptive Parameter-Efficient Learning for Multi-View ConvNets	102
LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models	101
Harnessing Multi-Modal Large Language Models for Measuring and Interpreting Color Differences	98
Multi-Granularity Contrastive Cross-Modal Collaborative Generation for End-to-End Long-Term Video Question Answering	98
Fine-Grained Recognition With Learnable Semantic Data Augmentation	97
Attention-Guided Neural Networks for Full-Reference and No-Reference Audio-Visual Quality Assessment	96
Fast 3D Room Layout Estimation Based on Compact High-Level Representation	95
HAIMNet: A Hierarchical Adaptive Interaction Modulation Network for Low-Light Image Enhancement	95
Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning	92
Perceptually Weighted Rate Distortion Optimization for Video-Based Point Cloud Compression	91
Spatial-Temporal Scene Graph Generation for Open-Vocabulary Multiple Object Tracking	89
Toward Generalizable Forgery Detection and Reasoning	87
ScaleNet: Scaling up Pretrained Neural Networks With Incremental Parameters	85
FD-SCU: Frequency Decomposition-Based Spectrum Collaborative Upsampling for Point Cloud Color Attribute	85
Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs	83
Optimization-Inspired Learning With Architecture Augmentations and Control Mechanisms for Low-Level Vision	83
SharpFormer: Learning Local Feature Preserving Global Representations for Image Deblurring	82
MicroSDF: Microfacet-Driven Hybrid Neural SDFs for Mixed-Reflectance Surface Reconstruction	82
MCIB: Multi-Modal Complementary Information Bottleneck for Hyperspectral and LiDAR Classification	81
SRS: Siamese Reconstruction-Segmentation Network Based on Dynamic-Parameter Convolution	81
Stacked Deconvolutional Network for Semantic Segmentation	80
Hyperspectral Meets Optical Flow: Spectral Flow Extraction for Hyperspectral Image Classification	80
TSCCD: Temporal Self-Construction Cross-Domain Learning for Unsupervised Hyperspectral Change Detection	80
Rethinking Sampling Strategies for Unsupervised Person Re-Identification	79
NeuralDiffuser: Neuroscience-Inspired Diffusion Guidance for fMRI Visual Reconstruction	79
Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching	79
Toward Robust Alignment for Video Dehazing With Temporal Lookup Table	78
Point-Based Learnable Query Generator for Human–Object Interaction Detection	78
Unsupervised Modality-Transferable Video Highlight Detection With Representation Activation Sequence Learning	78
Decoupled Cross-Modal Phrase-Attention Network for Image-Sentence Matching	77
Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction	76

SegHSI: Semantic Segmentation of Hyperspectral Images With Limited Labeled Pixels	76
Boundary-Aware Prototype in Semi-Supervised Medical Image Segmentation	76