Residential Collegefalse
Status已發表Published
Video action recognition with Key-detail Motion Capturing based on motion spectrum analysis and multiscale feature fusion
Zhang, Ganghan1; Huang, Guoheng1; Chen, Haiyuan1; Pun, Chi Man2; Yu, Zhiwen3; Ling, Wing Kuen4
2022-01
Source PublicationVisual Computer
ISSN0178-2789
Abstract

At present, existing research works on action recognition are still not ideal, when most of the video content is redundant such as video clips without any object motion, and human actions in the video are complex. The reasons are as follows: (1) Most of them lack attention to key-motion information of the video, thus irrelevant information will be input into the model. (2) And there is a lack of interaction between video spatial and temporal information, which may cause the loss of detailed motion information in the video. In this paper, we propose a Key-detail Motion Capturing Network (K-MCN) to solve these problems, which contains two modules. The first one is the Video Key-motion Spectrum Analyzer (VKSA) module. In this module, the video optical flow can be subjected to frequency spectrum analysis, filtering and clustering to extract the key-motion frames. The second one is the Multiscale Motion Spatiotemporal Interaction module, which allows multi-scale modeling and fusion of spatial and temporal features extracted from key-motion frames, enabling the network to realize the interaction and supplement of multiscale spatiotemporal information. Finally, we conducted extensive experiments on the UCF101, HMDB51 and Something-SomethingV1 datasets, and the results showed that our method achieves better performance compared with other state-of-the-art methods.

KeywordAction Recognition Key Frame Extraction Multiscale Feature Fusion Spatiotemporal Feature Pyramid
DOI10.1007/s00371-021-02355-4
URLView the original
Indexed BySCIE
Language英語English
WOS Research AreaComputer Science
WOS SubjectComputer Science, Software Engineering
WOS IDWOS:000741634600006
Scopus ID2-s2.0-85122962234
Fulltext Access
Citation statistics
Cited Times [WOS]:1   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorHuang, Guoheng
Affiliation1.School of Computers, Guangdong University of Technology, Guangzhou, 510006, China
2.Department of Computer and Information Science, University of Macau, 999078, Macao
3.School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510006, China
4.School of Information Engineering, Guangdong University of Technology, Guangzhou, 510006, China
Recommended Citation
GB/T 7714
Zhang, Ganghan,Huang, Guoheng,Chen, Haiyuan,et al. Video action recognition with Key-detail Motion Capturing based on motion spectrum analysis and multiscale feature fusion[J]. Visual Computer,2022.
APA Zhang, Ganghan,Huang, Guoheng,Chen, Haiyuan,Pun, Chi Man,Yu, Zhiwen,&Ling, Wing Kuen.(2022).Video action recognition with Key-detail Motion Capturing based on motion spectrum analysis and multiscale feature fusion.Visual Computer.
MLA Zhang, Ganghan,et al."Video action recognition with Key-detail Motion Capturing based on motion spectrum analysis and multiscale feature fusion".Visual Computer (2022).
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Ganghan]'s Articles
[Huang, Guoheng]'s Articles
[Chen, Haiyuan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Ganghan]'s Articles
[Huang, Guoheng]'s Articles
[Chen, Haiyuan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Ganghan]'s Articles
[Huang, Guoheng]'s Articles
[Chen, Haiyuan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.