Sparse representation for action recognition

Jiangen Zhang*, Yongtian Wang, Jing Chen, Qin Li

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

3 引用 (Scopus)

摘要

This paper presents an algorithm based on the ideas of bag of words and sparse representation for action recognition. We assume that all action instances form an action space and all action instances from one action class form a subspace of it. Furthermore, the action space can be represented by an over complete basis and each action instance can be represented by a linear combination of the basis. Naturally, the representation is sparse, so we can solve the problem via l1-minimization. Then the action instance is recognized by how well the basis of one class represents it. Our algorithm is tested on the largest action dataset: KHT dataset. The result shows that our algorithm can work well within a relative small train set.

源语言英语
主期刊名Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010
372-376
页数5
DOI
出版状态已出版 - 2010
活动2010 3rd International Congress on Image and Signal Processing, CISP 2010 - Yantai, 中国
期限: 16 10月 201018 10月 2010

出版系列

姓名Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010
1

会议

会议2010 3rd International Congress on Image and Signal Processing, CISP 2010
国家/地区中国
Yantai
时期16/10/1018/10/10

指纹

探究 'Sparse representation for action recognition' 的科研主题。它们共同构成独一无二的指纹。

引用此