Weakly supervised learning of actions from transcripts.

Computer Vision and Image Understanding(2017)

引用 109|浏览94
暂无评分
摘要
•A HMM based system for weakly supervised action segmentation is proposed.•Only a sequence of occurring actions is needed, no framewise annotation required.•CNN features can easily be included in the framework.•Our model shows state-of-the-art performance on various datasets.
更多
查看译文
关键词
Weak learning,Action recognition,Action classification,Temporal segmentation
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