OOIR: Observatory of International Research

Papers

(The H4-Index of Computer Vision and Image Understanding is 27. 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 2020-03-01 to 2024-03-01.)

Article	Citations
UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking	258
Monocular human pose estimation: A survey of deep learning-based methods	244
Skeleton-based action recognition via spatial and temporal transformer networks	133
Deep 3D human pose estimation: A review	123
Video anomaly detection and localization via Gaussian Mixture Fully Convolutional Variational Autoencoder	120
Pyramid Channel-based Feature Attention Network for image dehazing	108
Deep learning for deepfakes creation and detection: A survey	80
Pros and cons of GAN evaluation measures: New developments	77
A review of 3D human pose estimation algorithms for markerless motion capture	74
Fake face detection via adaptive manipulation traces extraction network	64
TCLR: Temporal contrastive learning for video representation	57
Infrared and visible image fusion via gradientlet filter	46
Single-image deblurring with neural networks: A comparative survey	46
Adversarial autoencoders for compact representations of 3D point clouds	43
High-level prior-based loss functions for medical image segmentation: A survey	43
A comprehensive review of past and present image inpainting methods	43
Knowledge distillation for incremental learning in semantic segmentation	42
CUFD: An encoder–decoder network for visible and infrared image fusion based on common and unique feature decomposition	38
Age estimation from faces using deep learning: A comparative analysis	36
Nighttime image dehazing based on Retinex and dark channel prior using Taylor series expansion	34
Visual complexity analysis using deep intermediate-layer features	33
Multi-focus image fusion approach based on CNP systems in NSCT domain	31
Detection of Face Recognition Adversarial Attacks	29
Human action recognition in drone videos using a few aerial training examples	29
Adversarial examples for replay attacks against CNN-based face recognition with anti-spoofing capability	28

End-to-end deep learning-based fringe projection framework for 3D profiling of objects	27
Learning deep edge prior for image denoising	27