CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Boosted multi-class semi-supervised learning for human action recognition
Zhang, Tianzhu1,2; Liu, Si1,2; Xu, Changsheng1,2; Lu, Hanqing1,2
Source PublicationPATTERN RECOGNITION
2011-10-01
Volume44Issue:10-11Pages:2334-2342
SubtypeArticle
AbstractHuman action recognition is a challenging task due to significant intra-class variations, occlusion, and background clutter. Most of the existing work use the action models based on statistic learning algorithms for classification. To achieve good performance on recognition, a large amount of the labeled samples are therefore required to train the sophisticated action models. However, collecting labeled samples is labor-intensive. To tackle this problem, we propose a boosted multi-class semi-supervised learning algorithm in which the co-EM algorithm is adopted to leverage the information from unlabeled data. Three key issues are addressed in this paper. Firstly, we formulate the action recognition in a multi-class semi-supervised learning problem to deal with the insufficient labeled data and high computational expense. Secondly, boosted co-EM is employed for the semi-supervised model construction. To overcome the high dimensional feature space, weighted multiple discriminant analysis (WMDA) is used to project the features into low dimensional subspaces in which the Gaussian mixture models (GMM) are trained and boosting scheme is used to integrate the subspace models. Thirdly, we present the upper bound of the training error in multi-class framework, which is able to guide the novel classifier construction. In theory, the proposed solution is proved to minimize this upper error bound. Experimental results have shown good performance on public datasets. Crown Copyright (C) 2010 Published by Elsevier Ltd. All rights reserved.
KeywordSemi-supervised Learning Action Recognition Adaboost.mh Co-em
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000292849000012
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/3325
Collection模式识别国家重点实验室_图像与视频分析
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.China Singapore Inst Digital Media, Singapore 119615, Singapore
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhang, Tianzhu,Liu, Si,Xu, Changsheng,et al. Boosted multi-class semi-supervised learning for human action recognition[J]. PATTERN RECOGNITION,2011,44(10-11):2334-2342.
APA Zhang, Tianzhu,Liu, Si,Xu, Changsheng,&Lu, Hanqing.(2011).Boosted multi-class semi-supervised learning for human action recognition.PATTERN RECOGNITION,44(10-11),2334-2342.
MLA Zhang, Tianzhu,et al."Boosted multi-class semi-supervised learning for human action recognition".PATTERN RECOGNITION 44.10-11(2011):2334-2342.
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, Tianzhu]'s Articles
[Liu, Si]'s Articles
[Xu, Changsheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Tianzhu]'s Articles
[Liu, Si]'s Articles
[Xu, Changsheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Tianzhu]'s Articles
[Liu, Si]'s Articles
[Xu, Changsheng]'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.