OOIR: Observatory of International Research

Papers

(The H4-Index of International Journal of Computer Vision is 50. 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 2020-11-01 to 2024-11-01.)

Article	Citations
Knowledge Distillation: A Survey	1385
BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation	819
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking	796
Learning to Prompt for Vision-Language Models	667
Beyond Brightening Low-light Images	392
Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation	304
SDNet: A Versatile Squeeze-and-Decomposition Network for Real-Time Image Fusion	250
Human Action Recognition and Prediction: A Survey	224
The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection	208
Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset	168
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking	165
Benchmarking Low-Light Image Enhancement and Beyond	153
CLIP-Adapter: Better Vision-Language Models with Feature Adapters	150
OCNet: Object Context for Semantic Segmentation	149
Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100	146
Deep Image Deblurring: A Survey	146
EfficientPS: Efficient Panoptic Segmentation	142
You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network	142
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection	140
Unsupervised Scale-Consistent Depth Learning from Video	126
Comparison of Full-Reference Image Quality Models for Optimization of Image Processing Systems	115
Curriculum Learning: A Survey	112
Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis	97
On the Arbitrary-Oriented Object Detection: Classification Based Approaches Revisited	93
Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training	86

ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond	85
Explainability of Deep Vision-Based Autonomous Driving Systems: Review and Challenges	83
3D-FUTURE: 3D Furniture Shape with TextURE	81
VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change	75
GhostNets on Heterogeneous Devices via Cheap Operations	74
Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild	74
Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis	73
Context Autoencoder for Self-supervised Representation Learning	73
Learning Adaptive Attribute-Driven Representation for Real-Time RGB-T Tracking	72
AutoScale: Learning to Scale for Crowd Counting	69
Structure-Measure: A New Way to Evaluate Foreground Maps	66
Vis-MVSNet: Visibility-Aware Multi-view Stereo Network	66
3D Object Detection for Autonomous Driving: A Comprehensive Survey	64
Countering Malicious DeepFakes: Survey, Battleground, and Horizon	60
A Survey on Long-Tailed Visual Recognition	59
Scale-Aware Domain Adaptive Faster R-CNN	56
Synthetic Humans for Action Recognition from Unseen Viewpoints	55
Bridging Composite and Real: Towards End-to-End Deep Image Matting	55
Adaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters	55
Occluded Video Instance Segmentation: A Benchmark	54
Twin Contrastive Learning for Online Clustering	53
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild	52
Low-light Image Enhancement via Breaking Down the Darkness	52
An Exploration of Embodied Visual Exploration	52
Towards High Performance Human Keypoint Detection	51