OOIR: Observatory of International Research

Papers

(The H4-Index of Computer Vision and Image Understanding is 32. 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 2022-05-01 to 2026-05-01.)

Article	Citations
Luminance prior guided Low-Light 4C catenary image enhancement	381
Editorial Board	126
Efficient cross-information fusion decoder for semantic segmentation	115
CRML-Net: Cross-Modal Reasoning and Multi-Task Learning Network for tooth image segmentation	114
Deducing health cues from biometric data	111
Editorial Board	94
Improving the planarity and sharpness of monocularly estimated depth images using the Phong reflection model	88
Editorial Board	62
Exploring using jigsaw puzzles for out-of-distribution detection	54
Extending function mixture network for improved spectral super-resolution	52
Editorial Board	50
Editorial Board	50
MATTE: Multi-task multi-scale attention	50
Feature reconstruction and metric based network for few-shot object detection	48
Convolutional neural network framework for deepfake detection: A diffusion-based approach	46
Twin-SegNet: Dynamically coupled complementary segmentation networks for generalized medical image segmentation	44
Exploring the differences in adversarial robustness between ViT- and CNN-based models using novel metrics	42
RetSeg3D: Retention-based 3D semantic segmentation for autonomous driving	41
SNRD-Net: SNR-aware dual enhancement network for low-light images	40
Spatial Sensitive Grad-CAM++: Towards High-Quality Visual Explanations for Object Detectors via Weighted Combination of Gradient Maps	39
Lightweight feature point detection network with channel enhancement	38
Emerging image generation with flexible control of perceived difficulty	38
3D semantic segmentation based on spatial-aware convolution and shape completion for augmented reality applications	37
Modality adaptation via feature difference learning for depth human parsing	36
QB-MOTR: A simple query bootstrapping end-to-end multi-object tracking method with transformer	36

REST: A resolution preserving network for photorealistic style transfer via semantic distillation	35
Siamese self-supervised learning for fine-grained visual classification	35
Robust Teacher: Self-correcting pseudo-label-guided semi-supervised learning for object detection	35
Adaptive CNN filter pruning using global importance metric	34
RelFormer: Advancing contextual relations for transformer-based dense captioning	34
PConvSRGAN: Real-world super-resolution reconstruction with pure convolutional networks	33
Embedding AI ethics into the design and use of computer vision technology for consumer’s behaviour understanding	32