Continuous Multi-View Human Action Recognition | |
Wang Q(王强)2,3; Sun G(孙干)1,2; Dong JH(董家华)1,2,6; Wang QQ(王倩倩)5; Ding ZM(丁正明)4 | |
刊名 | IEEE Transactions on Circuits and Systems for Video Technology |
2021 | |
页码 | 1-12 |
关键词 | Lifelong Machine Learning Human Action Recognition Multi-view Learning Subspace Learning |
ISSN号 | 1051-8215 |
产权排序 | 1 |
英文摘要 | Human action recognition which recognizes human actions in a video is a fundamental task in computer vision field. Although multiple existing methods with single-view or multi-view have been presented for human action recognition, these recognition approaches cannot be extended into new action recognition or action classification tasks, as well as discover underlying correlations among different views. To tackle the above problem, this paper proposes a new lifelong multi-view subspace learning framework for continuous human action recognition, which could exploit the complementary information amongst different views from a lifelong learning perspective. More specifically, a set of view-specific libraries is established to gradually store the useful information within multiple views. As a new action recognition task comes, we decompose the model parameters into a set of embedded parameters over view-specific libraries. A latent representation subspace is constructed via encouraging it to be close to different view-specific libraries, which can leverage the high-order correlations among different views and further avoid partial information for action recognition task. Meanwhile, we propose to employ an alternating direction strategy to optimize our proposed method. Empirical studies on real-world multi-view action recognition datasets have shown that our proposed framework attains the superior recognition performance and saves the computational time when continually learning new action recognition tasks. |
语种 | 英语 |
资助机构 | National Natural Science Foundation of China (Grant No. 62003336, 62073205) ; National Postdoctoral Innovative Talents Support Program (BX20200353) ; State Key Laboratory of Robotics (No: 2022-Z06) ; Nature Foundation of Liaoning Province of China under Grant (2020-KF-11-01) |
内容类型 | 期刊论文 |
源URL | [http://ir.sia.cn/handle/173321/29674] |
专题 | 沈阳自动化研究所_机器人学研究室 |
通讯作者 | Sun G(孙干) |
作者单位 | 1.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China 3.Key Laboratory of Manufacturing Industrial Integrated, Shenyang University, Shenyang, China 4.Department of Computer Science, Tulane University, New Orleans, LA 70118, USA. 5.Xidian University. Xian, Shanxi, 710071, China 6.University of Chinese Academy of Sciences, Beijing |
推荐引用方式 GB/T 7714 | Wang Q,Sun G,Dong JH,et al. Continuous Multi-View Human Action Recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology,2021:1-12. |
APA | Wang Q,Sun G,Dong JH,Wang QQ,&Ding ZM.(2021).Continuous Multi-View Human Action Recognition.IEEE Transactions on Circuits and Systems for Video Technology,1-12. |
MLA | Wang Q,et al."Continuous Multi-View Human Action Recognition".IEEE Transactions on Circuits and Systems for Video Technology (2021):1-12. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论