Learning semantic context feature-tree for action recognition via nearest neighbor fusion
详细信息 查看全文
- 作者：Tongchi ZhouAuthor Vitae ; Nijun LiAuthor Vitae ; Xu ChengAuthor Vitae ; Qinjun XuAuthor Vitae ; Lin ZhouAuthor Vitae ; Zhenyang WuAuthor Vitae
- 关键词：Feature-tree ; Semantic context ; Nearest neighbor fusion ; Action recognition
- 刊名：Neurocomputing
- 出版年：2016
- 出版时间：12 August 2016
- 年：2016
- 卷：201
- 期：Complete
- 页码：1-11
- 全文大小：4000 K
文摘
- •
We exploit super-pixel to obtain semantic motion regions that determine spatial co-occurrence domains.
- •
To capture the co-occurrence statistics at multiple temporal scales and build the relationships of them, a tree-structured model is built by a recursive manner.
- •
High node is generated by fusing the low layer associated nodes which are connected by the patch matching.