OOIR: Observatory of International Research

Papers

(The H4-Index of Computer Vision and Image Understanding is 28. 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 2021-10-01 to 2025-10-01.)

Article	Citations
Editorial Board	286
Editorial Board	232
Editorial Board	147
Editorial Board	109
Luminance prior guided Low-Light 4C catenary image enhancement	105
Editorial Board	91
Improving the planarity and sharpness of monocularly estimated depth images using the Phong reflection model	88
Exploring using jigsaw puzzles for out-of-distribution detection	84
Siamese self-supervised learning for fine-grained visual classification	76
Deducing health cues from biometric data	71
3D semantic segmentation based on spatial-aware convolution and shape completion for augmented reality applications	49
Convolutional neural network framework for deepfake detection: A diffusion-based approach	45
Twin-SegNet: Dynamically coupled complementary segmentation networks for generalized medical image segmentation	40
Feature reconstruction and metric based network for few-shot object detection	39
RetSeg3D: Retention-based 3D semantic segmentation for autonomous driving	38
Exploring the differences in adversarial robustness between ViT- and CNN-based models using novel metrics	36
Efficient cross-information fusion decoder for semantic segmentation	36
Emerging image generation with flexible control of perceived difficulty	35
CRML-Net: Cross-Modal Reasoning and Multi-Task Learning Network for tooth image segmentation	34
Extending function mixture network for improved spectral super-resolution	33
Modality adaptation via feature difference learning for depth human parsing	31
MATTE: Multi-task multi-scale attention	30
Robust Teacher: Self-correcting pseudo-label-guided semi-supervised learning for object detection	30
Lightweight feature point detection network with channel enhancement	30
Editorial Board	29

Editorial Board	29
RelFormer: Advancing contextual relations for transformer-based dense captioning	28
GaitBranch: A multi-branch refinement model combined with frame-channel attention mechanism for gait recognition	28
PConvSRGAN: Real-world super-resolution reconstruction with pure convolutional networks	28