3 papers
cs.CV2026
Vision-Language Model Purified Semi-Supervised Semantic Segmentation for Remote Sensing Images
Shanwen Wang, Xin Sun, Danfeng Hong +1
The semi-supervised semantic segmentation (S4) can learn rich visual knowledge from low-cost unlabeled images. However, traditional S4 architectures all face the challenge of low-q…
cs.CV2025
PRISM: Progressive Rain removal with Integrated State-space Modeling
Pengze Xue, Shanwen Wang, Fei Zhou +2
Image deraining is an essential vision technique that removes rain streaks and water droplets, enhancing clarity for critical vision tasks like autonomous driving. However, current…
cs.CV2025
Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network
Fei Zhou, Yi Li, Mingqing Zhu
In this paper, the dual-optical attention fusion crowd head point counting model (TAPNet) is proposed to address the problem of the difficulty of accurate counting in complex scene…