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 2022-06-01 to 2026-06-01.)

Article	Citations
Luminance prior guided Low-Light 4C catenary image enhancement	391
Editorial Board	129
Editorial Board	117
Improving the planarity and sharpness of monocularly estimated depth images using the Phong reflection model	116
Editorial Board	114
Exploring using jigsaw puzzles for out-of-distribution detection	98
Extending function mixture network for improved spectral super-resolution	89
MATTE: Multi-task multi-scale attention	66
Editorial Board	60
Editorial Board	53
3D semantic segmentation based on spatial-aware convolution and shape completion for augmented reality applications	52
Efficient cross-information fusion decoder for semantic segmentation	50
Emerging image generation with flexible control of perceived difficulty	50
Lightweight feature point detection network with channel enhancement	50
Modality adaptation via feature difference learning for depth human parsing	49
Siamese self-supervised learning for fine-grained visual classification	44
REST: A resolution preserving network for photorealistic style transfer via semantic distillation	44
Spatial Sensitive Grad-CAM++: Towards High-Quality Visual Explanations for Object Detectors via Weighted Combination of Gradient Maps	43
RetSeg3D: Retention-based 3D semantic segmentation for autonomous driving	42
JEMA: Joint Embedding of Multimodal and multi-view Alignment in human-centric embedding space for manufacturing	41
Convolutional neural network framework for deepfake detection: A diffusion-based approach	40
SNRD-Net: SNR-aware dual enhancement network for low-light images	40
Feature reconstruction and metric based network for few-shot object detection	38
Exploring the differences in adversarial robustness between ViT- and CNN-based models using novel metrics	38
Deducing health cues from biometric data	38

Twin-SegNet: Dynamically coupled complementary segmentation networks for generalized medical image segmentation	37
CRML-Net: Cross-Modal Reasoning and Multi-Task Learning Network for tooth image segmentation	36
QB-MOTR: A simple query bootstrapping end-to-end multi-object tracking method with transformer	35
Robust Teacher: Self-correcting pseudo-label-guided semi-supervised learning for object detection	35
NaviFormer: Multimodal scene segmentation for assistive navigation	35
RelFormer: Advancing contextual relations for transformer-based dense captioning	34
Feature preserving 3D mesh denoising with a Dense Local Graph Neural Network	33