Boosted multi-class semi-supervised learning for human action recognition

	Boosted multi-class semi-supervised learning for human action recognition
	Zhang, Tianzhu1,2 ; Liu, Si 1,2; Xu, Changsheng1,2 ; Lu, Hanqing1,2
发表期刊	PATTERN RECOGNITION
	2011-10-01
卷号	44 期号:10-11 页码:2334-2342
文章类型	Article
摘要	Human 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.
关键词	Semi-supervised Learning Action Recognition Adaboost.mh Co-em
WOS标题词	Science & Technology ; Technology
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000292849000012
引用统计	被引频次：28[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/3325
专题	紫东太初大模型研究中心_图像与视频分析
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.China Singapore Inst Digital Media, Singapore 119615, Singapore
第一作者单位	模式识别国家重点实验室
推荐引用方式 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.