2 papers
cs.CV2025
THAT: Token-wise High-frequency Augmentation Transformer for Hyperspectral Pansharpening
Hongkun Jin, Hongcheng Jiang, Zejun Zhang +4
Transformer-based methods have demonstrated strong potential in hyperspectral pansharpening by modeling long-range dependencies. However, their effectiveness is often limited by re…
cs.CV2024
Deformable-Heatmap-Segmentation for Automobile Visual Perception
Hongyu Jin
Semantic segmentation of road elements in 2D images is a crucial task in the recognition of some static objects such as lane lines and free space. In this paper, we propose DHSNet,…