SIA OpenIR  > 机器人学研究室
An Unsupervised Feature learning and clustering method for key frame extraction on human action recognition
Pei XM(裴晓敏); Fan BJ(范保杰); Tang YD(唐延东)
Department机器人学研究室
Conference Name7th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017
Conference DateJuly 31 - August 4, 2017
Conference PlaceHawaii, USA
Author of SourceIEEE Robotics and Automation Society
Source Publication2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017
PublisherIEEE
Publication PlaceNew York
2017
Pages759-762
Indexed ByEI ; CPCI(ISTP)
EI Accession number20183905873431
WOS IDWOS:000447628700138
Contribution Rank1
ISBN978-1-5386-0489-2
KeywordHuman Action Recognition Learning Feature Stacked Aut-encoder Affinity Propagation Clustering
Abstract

Human action recognition in video is an active research topic in computer vision. However, with the growing convenience of capturing and sharing videos, there are a growing variety of human action datasets with substantial amount of videos make human action recognition challenging problems, which can be solved by key frame extraction. Feature Clustering methods are usually employed to extract key frames. One difficulty is caused by the large variety of visual content in videos, makes hand-craft feature is not always effective, since there are no fixed descriptors can describe all video cases. Another difficulty is that traditional clustering algorithms are sensitive to the choice of initial clustering centers. An Unsupervised feature learning and clustering method is proposed for key frame extraction on human action recognition, Stacked auto-encoder(SAE) is trained using videos from 10 different human actions, after training, SAE is used as a feature extractor to learn features representing human actions. Affinity Propagation Clustering algorithm is used to select key frames from video sequences. Experiments using a variety of videos demonstrate that our method can be effectively summarizing video shots considering different human actions.

Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/21343
Collection机器人学研究室
Corresponding AuthorPei XM(裴晓敏)
AffiliationState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Science, Shenyang 110016, China
Recommended Citation
GB/T 7714
Pei XM,Fan BJ,Tang YD. An Unsupervised Feature learning and clustering method for key frame extraction on human action recognition[C]//IEEE Robotics and Automation Society. New York:IEEE,2017:759-762.
Files in This Item: Download All
File Name/Size DocType Version Access License
An Unsupervised Feat(1371KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Pei XM(裴晓敏)]'s Articles
[Fan BJ(范保杰)]'s Articles
[Tang YD(唐延东)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Pei XM(裴晓敏)]'s Articles
[Fan BJ(范保杰)]'s Articles
[Tang YD(唐延东)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Pei XM(裴晓敏)]'s Articles
[Fan BJ(范保杰)]'s Articles
[Tang YD(唐延东)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: An Unsupervised Feature learning and clustering method for key frame extraction on human action recognition.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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