OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE Transactions on Image Processing is 71. 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 2020-05-01 to 2024-05-01.)

Article	Citations
EnlightenGAN: Deep Light Enhancement Without Paired Supervision	871
Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding	326
JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation	275
CGNet: A Light-Weight Context Guided Network for Semantic Segmentation	270
LayerCAM: Exploring Hierarchical Class Activation Maps for Localization	260
Underwater Image Enhancement via Minimal Color Loss and Locally Adaptive Contrast Enhancement	204
UIU-Net: U-Net in U-Net for Infrared Small Object Detection	203
Self-Supervised Deep Correlation Tracking	199
Hierarchical Alternate Interaction Network for RGB-D Salient Object Detection	171
Weighted Feature Fusion of Convolutional Neural Network and Graph Attention Network for Hyperspectral Image Classification	170
Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images	166
Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement	159
On Data Augmentation for GAN Training	158
GMNet: Graded-Feature Multilabel-Learning Network for RGB-Thermal Urban Scene Semantic Segmentation	158
RefineDNet: A Weakly Supervised Refinement Framework for Single Image Dehazing	157
Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors	148
Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild	147
Vision Transformers for Single Image Dehazing	147
Dense Nested Attention Network for Infrared Small Target Detection	145
DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection	145
End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling	139
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content	139
Bilateral Attention Network for RGB-D Salient Object Detection	123
SAMNet: Stereoscopically Attentive Multi-Scale Network for Lightweight Salient Object Detection	122
A Supervised Segmentation Network for Hyperspectral Image Classification	121

AMP-Net: Denoising-Based Deep Unfolding for Compressive Image Sensing	119
Twin Adversarial Contrastive Learning for Underwater Image Enhancement and Beyond	117
Learning Deep Global Multi-Scale and Local Attention Features for Facial Expression Recognition in the Wild	116
Learning Guided Convolutional Network for Depth Completion	116
Fast Parameter-Free Multi-View Subspace Clustering With Consensus Anchor Guidance	114
Domain Adaptive Ensemble Learning	114
Spatial-Spectral Structured Sparse Low-Rank Representation for Hyperspectral Image Super-Resolution	113
Learning Spatial Attention for Face Super-Resolution	113
Stacked Deconvolutional Network for Semantic Segmentation	110
Rethinking the Competition Between Detection and ReID in Multiobject Tracking	108
DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking	107
Generalized Nonconvex Low-Rank Tensor Approximation for Multi-View Subspace Clustering	106
Delving Deep Into Label Smoothing	104
IDE: Image Dehazing and Exposure Using an Enhanced Atmospheric Scattering Model	104
Multi-Interactive Dual-Decoder for RGB-Thermal Salient Object Detection	102
DeepQTMT: A Deep Learning Approach for Fast QTMT-Based CU Partition of Intra-Mode VVC	100
AP-CNN: Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification	100
Latent Correlation Representation Learning for Brain Tumor Segmentation With Missing MRI Modalities	99
MATR: Multimodal Medical Image Fusion via Multiscale Adaptive Transformer	98
Model-Guided Deep Hyperspectral Image Super-Resolution	97
CDNet: Complementary Depth Network for RGB-D Salient Object Detection	94
Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images	93
Single-Source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification	91
Rotation-Invariant Attention Network for Hyperspectral Image Classification	89
Dynamic Selection Network for Image Inpainting	89
Adaptively Learning Facial Expression Representation via C-F Labels and Distillation	88
Adaptive Context-Aware Multi-Modal Network for Depth Completion	88
TCGL: Temporal Contrastive Graph for Self-Supervised Video Representation Learning	88
Ratio-and-Scale-Aware YOLO for Pedestrian Detection	87
Structure-Aware Positional Transformer for Visible-Infrared Person Re-Identification	86
Reduced Reference Perceptual Quality Model With Application to Rate Control for Video-Based Point Cloud Compression	83
HDR-GAN: HDR Image Reconstruction From Multi-Exposed LDR Images With Large Motions	82
Holistic LSTM for Pedestrian Trajectory Prediction	81
BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification	81
Light Field Image Super-Resolution Using Deformable Convolution	80
DSNet: A Flexible Detect-to-Summarize Network for Video Summarization	79
A Global-Local Self-Adaptive Network for Drone-View Object Detection	78
Jointly Modeling Motion and Appearance Cues for Robust RGB-T Tracking	78
Pseudo-Supervised Deep Subspace Clustering	76
Plant Disease Recognition: A Large-Scale Benchmark Dataset and a Visual Region and Loss Reweighting Approach	74
Joint Local and Global Information Learning With Single Apex Frame Detection for Micro-Expression Recognition	73
Band Representation-Based Semi-Supervised Low-Light Image Enhancement: Bridging the Gap Between Signal Fidelity and Perceptual Quality	73
EDN: Salient Object Detection via Extremely-Downsampled Network	72
Depth-Quality-Aware Salient Object Detection	72
A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection	72
Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation	72
Exploring Rich and Efficient Spatial Temporal Interactions for Real-Time Video Salient Object Detection	71
Bifurcated Backbone Strategy for RGB-D Salient Object Detection	71