SDA-CLIP: surgical visual domain adaptation using video and text labels.

Yuchong Li,Shuangfu Jia, Guangbi Song,Ping Wang,Fucang Jia

Quantitative imaging in medicine and surgery（2023）

引用 0|浏览3

暂无评分

摘要

The proposed SDA-CLIP model can effectively extract video scene information and textual semantic information, which greatly improves the performance of cross-domain surgical action recognition. The code is available at https://github.com/Lycus99/SDA-CLIP.

查看译文

关键词

surgical visual domain adaptation,text labels,sda-clip

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要