Semi-Supervised Image-to-Video Adaptation for Video Action Recognition.

IEEE Transactions on Cybernetics(2017)

引用 65|浏览49
暂无评分
摘要
Human action recognition has been well explored in applications of computer vision. Many successful action recognition methods have shown that action knowledge can be effectively learned from motion videos or still images. For the same action, the appropriate action knowledge learned from different types of media, e.g., videos or images, may be related. However, less effort has been made to improv...
更多
查看译文
关键词
Feature extraction,Image recognition,Computer science,Training,Semantics,Computer vision,Cameras
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