CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Learning discriminative context models for concurrent collective activity recognition
Zhao, Chaoyang; Wang, Jinqiao; Lu, Hanqing
Source PublicationMULTIMEDIA TOOLS AND APPLICATIONS
2017-03-01
Volume76Issue:5Pages:7401-7420
SubtypeArticle
AbstractCollective activity classification is the task to identify activities with multiple persons participation, which often involves the context information like person relationships and person interactions. Most existing approaches assume that all individuals in a single image share the same activity label. However, in many cases, multiple activities co-exist and serve as context cues for each other in real-world scenarios. Based on this observation, in this paper, a unified discriminative learning framework of multiple context models is proposed for concurrent collective activity recognition. Firstly, both the intra-class and inter-class behaviour interactions among persons in a scenario are considered. Besides, the scenario where activities happen also provides additional context information for recognizing specific collective activities. Finally, we jointly model the multiple context cues (intra-class, inter-class and global-context) with a max-margin leaning framework. A greedy forward search method is utilized to label the activities in the testing scenes. Experimental results demonstrate the superiority of our approach in activity recognition.
KeywordActivity Classification Context Information Max-margin Learning
WOS HeadingsScience & Technology ; Technology
DOI10.1007/s11042-016-3393-3
WOS KeywordSPACE
Indexed BySCI
Language英语
Funding Organization863 Program(2014AA015104) ; National Natural Science Foundation of China(61273034 ; 61332016)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000397278400058
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/14425
Collection模式识别国家重点实验室_图像与视频分析
AffiliationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhao, Chaoyang,Wang, Jinqiao,Lu, Hanqing. Learning discriminative context models for concurrent collective activity recognition[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2017,76(5):7401-7420.
APA Zhao, Chaoyang,Wang, Jinqiao,&Lu, Hanqing.(2017).Learning discriminative context models for concurrent collective activity recognition.MULTIMEDIA TOOLS AND APPLICATIONS,76(5),7401-7420.
MLA Zhao, Chaoyang,et al."Learning discriminative context models for concurrent collective activity recognition".MULTIMEDIA TOOLS AND APPLICATIONS 76.5(2017):7401-7420.
Files in This Item:
File Name/Size DocType Version Access License
Multimed Tools Appl.(2800KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhao, Chaoyang]'s Articles
[Wang, Jinqiao]'s Articles
[Lu, Hanqing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao, Chaoyang]'s Articles
[Wang, Jinqiao]'s Articles
[Lu, Hanqing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao, Chaoyang]'s Articles
[Wang, Jinqiao]'s Articles
[Lu, Hanqing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Multimed Tools Appl.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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