CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Boosted Exemplar Learning for Action Recognition and Annotation
Zhang, Tianzhu1,2; Liu, Jing1,2; Liu, Si1,2; Xu, Changsheng1,2; Lu, Hanqing1,2
Source PublicationIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
2011-07-01
Volume21Issue:7Pages:853-866
SubtypeArticle
AbstractHuman 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.
KeywordAction Annotation Action Recognition Adaboost Mi-svm Multiple Instance Learning (Mil)
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Language英语
WOS Research AreaEngineering
WOS SubjectEngineering, Electrical & Electronic
WOS IDWOS:000293684300001
Citation statistics
Cited Times:19[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/3324
Collection模式识别国家重点实验室_图像与视频分析
Affiliation1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
2.China Singapore Inst Digital Media, Singapore 119613, 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, 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.
Files in This Item: Download All
File Name/Size DocType Version Access License
Boosted Exemplar Lea(2004KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Tianzhu]'s Articles
[Liu, Jing]'s Articles
[Liu, Si]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Tianzhu]'s Articles
[Liu, Jing]'s Articles
[Liu, Si]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Tianzhu]'s Articles
[Liu, Jing]'s Articles
[Liu, Si]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Boosted Exemplar Learning for Action.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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