OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Image Processing is 73. 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 2021-05-01 to 2025-05-01.)

Article	Citations
Consensus Sparsity: Multi-Context Sparse Image Representation via L _∞-Induced Matrix Variate	470
Variational Structured Attention Networks for Deep Visual Representation Learning	462
Multiframe Joint Enhancement for Early Interlaced Videos	443
FF-LPD: A Real-Time Frame-by-Frame License Plate Detector With Knowledge Distillation and Feature Propagation	386
SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes With Cross-Object Consistency	332
HAda: Hyper-Adaptive Parameter-Efficient Learning for Multi-View ConvNets	304
Canonical Correlation Analysis With Low-Rank Learning for Image Representation	281
Learning Spectral Cues for Multispectral and Panchromatic Image Fusion	264
One-Class Classification Using ℓp-Norm Multiple Kernel Fisher Null Approach	214
Automatic Quaternion-Domain Color Image Stitching	212
Multi-Granularity Contrastive Cross-Modal Collaborative Generation for End-to-End Long-Term Video Question Answering	210
Toward Projected Clustering With Aggregated Mapping	199
A Low-Rank Tensor Decomposition Model With Factors Prior and Total Variation for Impulsive Noise Removal	188
Dual Alternating Direction Method of Multipliers for Inverse Imaging	163
Multimodal Unrolled Robust PCA for Background Foreground Separation	159
Density-Guided Incremental Dominant Instance Exploration for Two-View Geometric Model Fitting	159
A Fast and Efficient Shape Blending by Stable and Analytically Invertible Finite Descriptors	155
Self-Supervised Matting-Specific Portrait Enhancement and Generation	150
Graph Convolutional Dictionary Selection With L₂_, ₚ Norm for Video Summarization	150
Differentiable SAR Renderer and Image-Based Target Reconstruction	144
Contrast-Reconstruction Representation Learning for Self-Supervised Skeleton-Based Action Recognition	138
MaCon: A Generic Self-Supervised Framework for Unsupervised Multimodal Change Detection	138
GMLight: Lighting Estimation via Geometric Distribution Approximation	134
Harnessing Multi-modal Large Language Models for Measuring and Interpreting Color Differences	134
Cross-Modal Retrieval With Noisy Correspondence via Consistency Refining and Mining	130

Equivariant Local Reference Frames With Optimization for Robust Non-Rigid Point Cloud Correspondence	129
Discrete Metric Learning for Fast Image Set Classification	128
Pro2Diff: Proposal Propagation for Multi-Object Tracking via the Diffusion Model	124
TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation	120
Pose-Appearance Relational Modeling for Video Action Recognition	118
Cross-Modality Pyramid Alignment for Visual Intention Understanding	115
Uncertainty-Guided Refinement for Fine-Grained Salient Object Detection	115
Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments	114
Multi-Constraint Adversarial Networks for Unsupervised Image-to-Image Translation	110
Attention-Guided Neural Networks for Full-Reference and No-Reference Audio-Visual Quality Assessment	108
Bi-Nuclear Tensor Schatten-p Norm Minimization for Multi-View Subspace Clustering	105
Graph Embedding Contrastive Multi-Modal Representation Learning for Clustering	103
Real Image Denoising With a Locally-Adaptive Bitonic Filter	103
Fine-Grained Recognition With Learnable Semantic Data Augmentation	102
Attentive WaveBlock: Complementarity-Enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-Identification and Beyond	101
Few-Shot Learning With Class-Covariance Metric for Hyperspectral Image Classification	100
Bidirectional Mapping Coupled GAN for Generalized Zero-Shot Learning	99
Cross-Attentional Spatio-Temporal Semantic Graph Networks for Video Question Answering	98
Inverse Image Frequency for Long-Tailed Image Recognition	96
SharpFormer: Learning Local Feature Preserving Global Representations for Image Deblurring	95
Unsupervised Modality-Transferable Video Highlight Detection With Representation Activation Sequence Learning	95
Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction	94
Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning	93
Boundary-Aware Prototype in Semi-Supervised Medical Image Segmentation	92
Addressing Challenges of Incorporating Appearance Cues Into Heuristic Multi-Object Tracker via a Novel Feature Paradigm	90
SegHSI: Semantic Segmentation of Hyperspectral Images With Limited Labeled Pixels	90
Non-Cascaded and Crosstalk-Free Multi-Image Encryption Based on Optical Scanning Holography Using 2D Orthogonal Compressive Sensing	90
Grammar-Induced Wavelet Network for Human Parsing	88
Efficient Semi-Supervised Multimodal Hashing With Importance Differentiation Regression	88
Decoupled Cross-Modal Phrase-Attention Network for Image-Sentence Matching	88
Optimization-Inspired Learning With Architecture Augmentations and Control Mechanisms for Low-Level Vision	88
Point-Based Learnable Query Generator for Human–Object Interaction Detection	88
Distractor-Aware Event-Based Tracking	86
Stacked Deconvolutional Network for Semantic Segmentation	85
Unsupervised Person Re-Identification With Stochastic Training Strategy	85
Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching	84
Hyperspectral Meets Optical Flow: Spectral Flow Extraction for Hyperspectral Image Classification	83
Rethinking Sampling Strategies for Unsupervised Person Re-Identification	83
Coarse-to-Fine Contrastive Self-Supervised Feature Learning for Land-Cover Classification in SAR Images With Limited Labeled Data	81
Fuzzy Sparse Subspace Clustering for Infrared Image Segmentation	81
DUT: Learning Video Stabilization by Simply Watching Unstable Videos	80
IMU-Assisted Online Video Background Identification	79
Toward Video Anomaly Retrieval From Video Anomaly Detection: New Benchmarks and Model	76
NR-MVSNet: Learning Multi-View Stereo Based on Normal Consistency and Depth Refinement	75
Cross-Layer Contrastive Learning of Latent Semantics for Facial Expression Recognition	75
Commonality Feature Representation Learning for Unsupervised Multimodal Change Detection	74
Cyclic Self-Training With Proposal Weight Modulation for Cross-Supervised Object Detection	74
Multi-Exposure Image Fusion via Deformable Self-Attention	73