CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算与图形学
Hierarchical affective content analysis in arousal and valence dimensions
Xu, Min1,2; Xu, Changsheng2; He, Xiangjian1; Jin, Jesse S.3; Luo, Suhuai3; Rui, Yong
Source PublicationSIGNAL PROCESSING
2013-08-01
Volume93Issue:8Pages:2140-2150
SubtypeArticle
AbstractDifferent from the existing work focusing on emotion type detection, the proposed approach in this paper provides flexibility for users to pick up their favorite affective content by choosing either emotion intensity levels or emotion types. Specifically, we propose a hierarchical structure for movie emotions and analyze emotion intensity and emotion type by using arousal and valence related features hierarchically. Firstly, three emotion intensity levels are detected by using fuzzy c-mean clustering on arousal features. Fuzzy clustering provides a mathematical model to represent vagueness, which is close to human perception. Then, valence related features are used to detect five emotion types. Considering video is continuous time series data and the occurrence of a certain emotion is affected by recent emotional history, conditional random fields (CRFs) are used to capture the context information. Outperforming Hidden Markov Model, CRF relaxes the independence assumption for states required by HMM and avoids bias problem. Experimental results show that CRF-based hierarchical method outperforms the one-step method on emotion type detection. User study shows that majority of the viewers prefer to have option of accessing movie content by emotion intensity levels. Majority of the users are satisfied with the proposed emotion detection. (C) 2012 Elsevier B.V. All rights reserved.
KeywordAffective Content Detection Multiple Modalities Mid-level Representation
WOS HeadingsScience & Technology ; Technology
WOS KeywordVIDEO ; CLASSIFICATION ; FEATURES ; EMOTIONS ; FILM
Indexed BySCI
Language英语
WOS Research AreaEngineering
WOS SubjectEngineering, Electrical & Electronic
WOS IDWOS:000318581900005
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/2882
Collection模式识别国家重点实验室_多媒体计算与图形学
Affiliation1.Univ Technol Sydney, Sch Comp & Commun, Sydney, NSW 2007, Australia
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China
3.Univ Newcastle, Fac Sci & IT, Callaghan, NSW 2308, Australia
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Xu, Min,Xu, Changsheng,He, Xiangjian,et al. Hierarchical affective content analysis in arousal and valence dimensions[J]. SIGNAL PROCESSING,2013,93(8):2140-2150.
APA Xu, Min,Xu, Changsheng,He, Xiangjian,Jin, Jesse S.,Luo, Suhuai,&Rui, Yong.(2013).Hierarchical affective content analysis in arousal and valence dimensions.SIGNAL PROCESSING,93(8),2140-2150.
MLA Xu, Min,et al."Hierarchical affective content analysis in arousal and valence dimensions".SIGNAL PROCESSING 93.8(2013):2140-2150.
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
[Xu, Min]'s Articles
[Xu, Changsheng]'s Articles
[He, Xiangjian]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xu, Min]'s Articles
[Xu, Changsheng]'s Articles
[He, Xiangjian]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xu, Min]'s Articles
[Xu, Changsheng]'s Articles
[He, Xiangjian]'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.