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 2021-12-01 to 2025-12-01.)

Article	Citations
Luminance prior guided Low-Light 4C catenary image enhancement	307
Editorial Board	248
Efficient cross-information fusion decoder for semantic segmentation	116
3D semantic segmentation based on spatial-aware convolution and shape completion for augmented reality applications	113
Editorial Board	100
Robust Teacher: Self-correcting pseudo-label-guided semi-supervised learning for object detection	97
Siamese self-supervised learning for fine-grained visual classification	88
Emerging image generation with flexible control of perceived difficulty	85
Improving the planarity and sharpness of monocularly estimated depth images using the Phong reflection model	73
Editorial Board	52
Exploring using jigsaw puzzles for out-of-distribution detection	51
Extending function mixture network for improved spectral super-resolution	47
MATTE: Multi-task multi-scale attention	41
Deducing health cues from biometric data	40
Editorial Board	38
Editorial Board	37
Modality adaptation via feature difference learning for depth human parsing	35
Twin-SegNet: Dynamically coupled complementary segmentation networks for generalized medical image segmentation	35
Exploring the differences in adversarial robustness between ViT- and CNN-based models using novel metrics	34
Feature reconstruction and metric based network for few-shot object detection	34
RetSeg3D: Retention-based 3D semantic segmentation for autonomous driving	34
Lightweight feature point detection network with channel enhancement	33
Convolutional neural network framework for deepfake detection: A diffusion-based approach	33
CRML-Net: Cross-Modal Reasoning and Multi-Task Learning Network for tooth image segmentation	31
REST: A resolution preserving network for photorealistic style transfer via semantic distillation	31

Implicit and explicit commonsense for multi-sentence video captioning	30
RelFormer: Advancing contextual relations for transformer-based dense captioning	30
Reverse Stable Diffusion: What prompt was used to generate this image?	29
Iterative Caption Generation with Heuristic Guidance for enhancing knowledge-based visual question answering	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
Robust detection of dehazed images via dual-stream CNNs with adaptive feature fusion	28