中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 模式分析与学习团队
Cholesky Decomposition-Based Metric Learning for Video-Based Human Action Recognition

文献类型：期刊论文

作者Chen, Si3; Shen, Yuanyuan2; Yan, Yan1; Wang, Dahan3; Zhu, Shunzhi3
刊名IEEE ACCESS
出版日期2020
卷号8页码:36313-36321
关键词Human action recognition metric learning Cholesky decomposition
ISSN号2169-3536
DOI10.1109/ACCESS.2020.2966329
通讯作者Zhu, Shunzhi(ssz@xmut.edu.cn)
英文摘要Video-based human action recognition can understand human actions and behaviours in the video sequences, and has wide applications for health care, human-machine interaction and so on. Metric learning, which learns a similarity metric, plays an important role in human action recognition. However, learning a full-rank matrix is usually inefficient and easily leads to overfitting. In order to overcome the above issues, a common way is to impose the low-rank constraint on the learned matrix. This paper proposes a novel Cholesky decomposition based metric learning (CDML) method for effective video-based human action recognition. Firstly, the improved dense trajectories technique and the vector of locally aggregated descriptor (VLAD) are respectively used for feature detection and feature encoding. Then, considering the high dimensionality of VLAD features, we propose to learn a similarity matrix by taking advantage of Cholesky decomposition, which decomposes the matrix into the product between a lower triangular matrix and its symmetric matrix. Different from the traditional low-rank metric learning methods that explicitly adopt the low-rank constraint to learn the matrix, the proposed algorithm achieves such a constraint by controlling the rank of the lower triangular matrix, thus leading to high computational efficiency. Experimental results on the public video dataset show that the proposed method achieves the superior performance compared with several state-of-the-art methods.
WOS关键词HISTOGRAMS ; TIME
资助项目Natural Science Foundation of Fujian Province of China[2018J01576] ; Natural Science Foundation of Fujian Province of China[2017J01127] ; National Key Research and Development Program of China[2017YFB1302400] ; National Natural Science Foundation of China[61672442] ; National Natural Science Foundation of China[61773325] ; National Natural Science Foundation of China[61571379]
WOS研究方向Computer Science ; Engineering ; Telecommunications
语种英语
WOS记录号WOS:000524612800023
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Natural Science Foundation of Fujian Province of China ; National Key Research and Development Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/38703]  
专题自动化研究所_模式识别国家重点实验室_模式分析与学习团队
通讯作者Zhu, Shunzhi
作者单位1.Xiamen Univ, Sch Informat, Xiamen 361005, Peoples R China
2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
3.Xiamen Univ Technol, Sch Comp & Informat Engn, Xiamen 361024, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Si,Shen, Yuanyuan,Yan, Yan,et al. Cholesky Decomposition-Based Metric Learning for Video-Based Human Action Recognition[J]. IEEE ACCESS,2020,8:36313-36321.
APA Chen, Si,Shen, Yuanyuan,Yan, Yan,Wang, Dahan,&Zhu, Shunzhi.(2020).Cholesky Decomposition-Based Metric Learning for Video-Based Human Action Recognition.IEEE ACCESS,8,36313-36321.
MLA Chen, Si,et al."Cholesky Decomposition-Based Metric Learning for Video-Based Human Action Recognition".IEEE ACCESS 8(2020):36313-36321.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。