Computer Vision and Image Understanding

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 2021-09-01 to 2025-09-01.)
ArticleCitations
Editorial Board285
Editorial Board272
Editorial Board225
Editorial Board142
Improving the planarity and sharpness of monocularly estimated depth images using the Phong reflection model103
Editorial Board103
Exploring using jigsaw puzzles for out-of-distribution detection87
Feature reconstruction and metric based network for few-shot object detection84
Siamese self-supervised learning for fine-grained visual classification83
Luminance prior guided Low-Light 4C catenary image enhancement72
Robust Teacher: Self-correcting pseudo-label-guided semi-supervised learning for object detection71
3D semantic segmentation based on spatial-aware convolution and shape completion for augmented reality applications69
Exploring the differences in adversarial robustness between ViT- and CNN-based models using novel metrics49
Decoupled appearance and motion learning for efficient anomaly detection in surveillance video46
Emerging image generation with flexible control of perceived difficulty42
CRML-Net: Cross-Modal Reasoning and Multi-Task Learning Network for tooth image segmentation39
Extending function mixture network for improved spectral super-resolution39
Lightweight feature point detection network with channel enhancement34
Modality adaptation via feature difference learning for depth human parsing34
Deducing health cues from biometric data34
MATTE: Multi-task multi-scale attention33
Convolutional neural network framework for deepfake detection: A diffusion-based approach33
Twin-SegNet: Dynamically coupled complementary segmentation networks for generalized medical image segmentation32
Efficient cross-information fusion decoder for semantic segmentation32
RetSeg3D: Retention-based 3D semantic segmentation for autonomous driving31
Editorial Board29
Implicit and explicit commonsense for multi-sentence video captioning28
View-aligned pixel-level feature aggregation for 3D shape classification28
Syntactically and semantically enhanced captioning network via hybrid attention and POS tagging prompt28
Editorial Board28
Adaptive CNN filter pruning using global importance metric28
0.06657886505127