Boosted Exemplar Learning for Action Recognition and Annotation

	Boosted Exemplar Learning for Action Recognition and Annotation
	Zhang, Tianzhu1,2 ; Liu, Jing1,2 ; Liu, Si 1,2; Xu, Changsheng1,2 ; Lu, Hanqing1,2
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2011-07-01
卷号	21 期号:7 页码:853-866
文章类型	Article
摘要	Human action recognition and annotation is an active research topic in computer vision. How to model various actions, varying with time resolution, visual appearance, and others, is a challenging task. In this paper, we propose a boosted exemplar learning (BEL) approach to model various actions in a weakly supervised manner, i.e., only action bag-level labels are provided but action instance level ones are not. The proposed BEL method can be summarized as three steps. First, for each action category, amount of class-specific candidate exemplars are learned through an optimization formulation considering their discrimination and co-occurrence. Second, each action bag is described as a set of similarities between its instances and candidate exemplars. Instead of simply using a heuristic distance measure, the similarities are decided by the exemplar-based classifiers through the multiple instance learning, in which a positive (or negative) video or image set is deemed as a positive (or negative) action bag and those frames similar to the given exemplar in Euclidean Space as action instances. Third, we formulate the selection of the most discriminative exemplars into a boosted feature selection framework and simultaneously obtain an action bag-based detector. Experimental results on two publicly available datasets: the KTH dataset and Weizmann dataset, demonstrate the validity and effectiveness of the proposed approach for action recognition. We also apply BEL to learn representations of actions by using images collected from the Web and use this knowledge to automatically annotate action in YouTube videos. Results are very impressive, which proves that the proposed algorithm is also practical in unconstraint environments.
关键词	Action Annotation Action Recognition Adaboost Mi-svm Multiple Instance Learning (Mil)
WOS标题词	Science & Technology ; Technology
收录类别	SCI
语种	英语
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000293684300001
引用统计	被引频次：22[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/173211/3324
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, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.China Singapore Inst Digital Media, Singapore 119613, 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, Jing,Liu, Si,et al. Boosted Exemplar Learning for Action Recognition and Annotation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2011,21(7):853-866.
APA	Zhang, Tianzhu,Liu, Jing,Liu, Si,Xu, Changsheng,&Lu, Hanqing.(2011).Boosted Exemplar Learning for Action Recognition and Annotation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,21(7),853-866.
MLA	Zhang, Tianzhu,et al."Boosted Exemplar Learning for Action Recognition and Annotation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 21.7(2011):853-866.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Boosted Exemplar Lea（2004KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载