CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Learning Human Actions by Combining Global Dynamics and Local Appearance
Luo, Guan1; Yang, Shuang1; Tian, Guodong1; Yuan, Chunfeng1; Hu, Weiming1; Maybank, Stephen J.2; weiming hu
Source PublicationIEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
2014-12-01
Volume36Issue:12Pages:2466-2482
SubtypeArticle
AbstractIn this paper, we address the problem of human action recognition through combining global temporal dynamics and local visual spatio-temporal appearance features. For this purpose, in the global temporal dimension, we propose to model the motion dynamics with robust linear dynamical systems (LDSs) and use the model parameters as motion descriptors. Since LDSs live in a non-euclidean space and the descriptors are in non-vector form, we propose a shift invariant subspace angles based distance to measure the similarity between LDSs. In the local visual dimension, we construct curved spatio-temporal cuboids along the trajectories of densely sampled feature points and describe them using histograms of oriented gradients (HOG). The distance between motion sequences is computed with the Chi-Squared histogram distance in the bag-of-words framework. Finally we perform classification using the maximum margin distance learning method by combining the global dynamic distances and the local visual distances. We evaluate our approach for action recognition on five short clips data sets, namely Weizmann, KTH, UCF sports, Hollywood2 and UCF50, as well as three long continuous data sets, namely VIRAT, ADL and CRIM13. We show competitive results as compared with current state-of-the-art methods.
KeywordAction Recognition Linear Dynamical System Local Spatio-temporal Feature Non-vector Descriptor Distance Learning
WOS HeadingsScience & Technology ; Technology
WOS KeywordHUMAN ACTION CATEGORIES ; BINET-CAUCHY KERNELS ; TIME INTEREST POINTS ; ACTION RECOGNITION ; HUMAN MOTION ; SUBSPACE IDENTIFICATION ; TEXTURE RECOGNITION ; MODELS ; CLASSIFICATION ; SYSTEMS
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000344988000011
Citation statistics
Cited Times:15[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/3273
Collection模式识别国家重点实验室_视频内容安全
Corresponding Authorweiming hu
Affiliation1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
2.Univ London Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Luo, Guan,Yang, Shuang,Tian, Guodong,et al. Learning Human Actions by Combining Global Dynamics and Local Appearance[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2014,36(12):2466-2482.
APA Luo, Guan.,Yang, Shuang.,Tian, Guodong.,Yuan, Chunfeng.,Hu, Weiming.,...&weiming hu.(2014).Learning Human Actions by Combining Global Dynamics and Local Appearance.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,36(12),2466-2482.
MLA Luo, Guan,et al."Learning Human Actions by Combining Global Dynamics and Local Appearance".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 36.12(2014):2466-2482.
Files in This Item: Download All
File Name/Size DocType Version Access License
LearningHumanActions(1426KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Luo, Guan]'s Articles
[Yang, Shuang]'s Articles
[Tian, Guodong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Luo, Guan]'s Articles
[Yang, Shuang]'s Articles
[Tian, Guodong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Luo, Guan]'s Articles
[Yang, Shuang]'s Articles
[Tian, Guodong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: LearningHumanActions.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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