OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Image Processing is 81. 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 2021-09-01 to 2025-09-01.)

Article	Citations
Consensus Sparsity: Multi-Context Sparse Image Representation via L _∞-Induced Matrix Variate	617
HAda: Hyper-Adaptive Parameter-Efficient Learning for Multi-View ConvNets	580
Canonical Correlation Analysis With Low-Rank Learning for Image Representation	540
One-Class Classification Using ℓp-Norm Multiple Kernel Fisher Null Approach	495
Multi-Granularity Contrastive Cross-Modal Collaborative Generation for End-to-End Long-Term Video Question Answering	402
A Fast and Efficient Shape Blending by Stable and Analytically Invertible Finite Descriptors	401
Pro2Diff: Proposal Propagation for Multi-Object Tracking via the Diffusion Model	375
Automatic Quaternion-Domain Color Image Stitching	331
Spatial Frequency Modulation Network for Efficient Image Dehazing	314
Toward Projected Clustering With Aggregated Mapping	308
Self-Supervised Matting-Specific Portrait Enhancement and Generation	262
MaCon: A Generic Self-Supervised Framework for Unsupervised Multimodal Change Detection	254
Graph Convolutional Dictionary Selection With L₂_, ₚ Norm for Video Summarization	239
Equivariant Local Reference Frames With Optimization for Robust Non-Rigid Point Cloud Correspondence	216
Multi-Constraint Adversarial Networks for Unsupervised Image-to-Image Translation	210
Bi-Nuclear Tensor Schatten-p Norm Minimization for Multi-View Subspace Clustering	191
Harnessing Multi-modal Large Language Models for Measuring and Interpreting Color Differences	187
Density-Guided Incremental Dominant Instance Exploration for Two-View Geometric Model Fitting	180
STPNet: Scale-Aware Text Prompt Network for Medical Image Segmentation	178
FF-LPD: A Real-Time Frame-by-Frame License Plate Detector With Knowledge Distillation and Feature Propagation	177
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments	175
Multimodal Unrolled Robust PCA for Background Foreground Separation	175
GMLight: Lighting Estimation via Geometric Distribution Approximation	166
A Low-Rank Tensor Decomposition Model With Factors Prior and Total Variation for Impulsive Noise Removal	165
An Adaptive Multi-Granularity Graph Representation of Image via Granular-ball Computing	164

Variational Structured Attention Networks for Deep Visual Representation Learning	162
Cross-Modal Retrieval With Noisy Correspondence via Consistency Refining and Mining	157
Discrete Metric Learning for Fast Image Set Classification	154
Graph Embedding Contrastive Multi-Modal Representation Learning for Clustering	151
Attentive WaveBlock: Complementarity-Enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-Identification and Beyond	150
Multiframe Joint Enhancement for Early Interlaced Videos	150
Dual Alternating Direction Method of Multipliers for Inverse Imaging	146
Learning Spectral Cues for Multispectral and Panchromatic Image Fusion	133
Uncertainty-Guided Refinement for Fine-Grained Salient Object Detection	132
Real Image Denoising With a Locally-Adaptive Bitonic Filter	128
Differentiable SAR Renderer and Image-Based Target Reconstruction	127
AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation	124
Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments	123
SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes With Cross-Object Consistency	123
Attention-Guided Neural Networks for Full-Reference and No-Reference Audio-Visual Quality Assessment	121
Color Spike Camera Reconstruction via Long Short-Term Temporal Aggregation of Spike Signals	121
Cross-Modality Pyramid Alignment for Visual Intention Understanding	116
Pose-Appearance Relational Modeling for Video Action Recognition	116
TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation	115
Fine-Grained Recognition With Learnable Semantic Data Augmentation	115
Few-Shot Learning With Class-Covariance Metric for Hyperspectral Image Classification	114
Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction	113
Contrast-Reconstruction Representation Learning for Self-Supervised Skeleton-Based Action Recognition	113
Stacked Deconvolutional Network for Semantic Segmentation	111
Grammar-Induced Wavelet Network for Human Parsing	111
Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning	111
NR-MVSNet: Learning Multi-View Stereo Based on Normal Consistency and Depth Refinement	110
Bidirectional Mapping Coupled GAN for Generalized Zero-Shot Learning	110
Cross-Layer Contrastive Learning of Latent Semantics for Facial Expression Recognition	110
SharpFormer: Learning Local Feature Preserving Global Representations for Image Deblurring	110
Cross-Domain Diffusion With Progressive Alignment for Efficient Adaptive Retrieval	109
FsaNet: Frequency Self-Attention for Semantic Segmentation	109
Non-Cascaded and Crosstalk-Free Multi-Image Encryption Based on Optical Scanning Holography Using 2D Orthogonal Compressive Sensing	107
Interactive Face Video Coding: A Generative Compression Framework	107
Toward Video Anomaly Retrieval From Video Anomaly Detection: New Benchmarks and Model	106
DUT: Learning Video Stabilization by Simply Watching Unstable Videos	101
Point-Based Learnable Query Generator for Human–Object Interaction Detection	101
Precise Facial Landmark Detection by Reference Heatmap Transformer	98
Efficient Semi-Supervised Multimodal Hashing With Importance Differentiation Regression	98
Cross-Attentional Spatio-Temporal Semantic Graph Networks for Video Question Answering	97
Optimization-Inspired Learning With Architecture Augmentations and Control Mechanisms for Low-Level Vision	96
Fast 3D Room Layout Estimation Based on Compact High-Level Representation	96
Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion	96
Transition Is a Process: Pair-to-Video Change Detection Networks for Very High Resolution Remote Sensing Images	95
SegHSI: Semantic Segmentation of Hyperspectral Images With Limited Labeled Pixels	95
Boundary-Aware Prototype in Semi-Supervised Medical Image Segmentation	93
Cyclic Self-Training With Proposal Weight Modulation for Cross-Supervised Object Detection	91
NeuralDiffuser: Neuroscience-Inspired Diffusion Guidance for fMRI Visual Reconstruction	90
IMU-Assisted Online Video Background Identification	88
Rethinking Sampling Strategies for Unsupervised Person Re-Identification	87

Unsupervised Modality-Transferable Video Highlight Detection With Representation Activation Sequence Learning	86
Coarse-to-Fine Contrastive Self-Supervised Feature Learning for Land-Cover Classification in SAR Images With Limited Labeled Data	84
Addressing Challenges of Incorporating Appearance Cues Into Heuristic Multi-Object Tracker via a Novel Feature Paradigm	84
Hyperspectral Meets Optical Flow: Spectral Flow Extraction for Hyperspectral Image Classification	83
Inverse Image Frequency for Long-Tailed Image Recognition	83
Variational Bayes Image Restoration With Compressive Autoencoders	81