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 2021-08-01 to 2025-08-01.)

Article	Citations
Editorial Board	273
Editorial Board	257
Editorial Board	217
Editorial Board	140
Editorial Board	101
Improving the planarity and sharpness of monocularly estimated depth images using the Phong reflection model	100
Exploring using jigsaw puzzles for out-of-distribution detection	83
Feature reconstruction and metric based network for few-shot object detection	82
RetSeg3D: Retention-based 3D semantic segmentation for autonomous driving	80
Luminance prior guided Low-Light 4C catenary image enhancement	68
Siamese self-supervised learning for fine-grained visual classification	68
Robust Teacher: Self-correcting pseudo-label-guided semi-supervised learning for object detection	65
Twin-SegNet: Dynamically coupled complementary segmentation networks for generalized medical image segmentation	48
Deducing health cues from biometric data	45
Emerging image generation with flexible control of perceived difficulty	39
3D semantic segmentation based on spatial-aware convolution and shape completion for augmented reality applications	39
CRML-Net: Cross-Modal Reasoning and Multi-Task Learning Network for tooth image segmentation	38
MATTE: Multi-task multi-scale attention	34
Extending function mixture network for improved spectral super-resolution	34
Modality adaptation via feature difference learning for depth human parsing	33
Lightweight feature point detection network with channel enhancement	32
Convolutional neural network framework for deepfake detection: A diffusion-based approach	31
Efficient cross-information fusion decoder for semantic segmentation	30
Decoupled appearance and motion learning for efficient anomaly detection in surveillance video	29
Syntactically and semantically enhanced captioning network via hybrid attention and POS tagging prompt	27

Adaptive CNN filter pruning using global importance metric	27
Editorial Board	27
Implicit and explicit commonsense for multi-sentence video captioning	27
View-aligned pixel-level feature aggregation for 3D shape classification	27
Exploring the differences in adversarial robustness between ViT- and CNN-based models using novel metrics	27
Editorial Board	27
3D object feature extraction and classification using 3D MF-DFA	27