Manifold Warp Segmentation of Human Action
Liu, Shenglan1; Feng, Lin1; Liu, Yang1; Qiao, Hong2,3; Wu, Jun1; Wang, Wei1
Source PublicationIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
2018-05-01
Volume29Issue:5Pages:1414-1426
SubtypeArticle
AbstractHuman action segmentation is important for human action analysis, which is a highly active research area. Most segmentation methods are based on clustering or numerical descriptors, which are only related to data, and consider no relationship between the data and physical characteristics of human actions. Physical characteristics of human motions are those that can be directly perceived by human beings, such as speed, acceleration, continuity, and so on, which are quite helpful in detecting human motion segment points. We propose a new physical-based descriptor of human action by curvature sequence warp space alignment (CSWSA) approach for sequence segmentation in this paper. Furthermore, time series-warp metric curvature segmentation method is constructed by the proposed descriptor and CSWSA. In our segmentation method, descriptor can express the changes of human actions, and CSWSA is an auxiliary method to give suggestions for segmentation. The experimental results show that our segmentation method is effective in both CMU human motion and video-based data sets.
KeywordCurvature Dimensionality Reduction Human Action Segmentation Space Alignment
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TNNLS.2017.2672971
WOS KeywordMOTION SYNTHESIS ; CLASSIFICATION ; RECOGNITION ; RETRIEVAL
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(61210009 ; China Postdoctoral Science Foundation(ZX20150629) ; 61370200 ; 61602082)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000430729100002
Citation statistics
Cited Times:2[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20099
Collection复杂系统管理与控制国家重点实验室_机器人理论与应用
Affiliation1.Dalian Univ Technol, Fac Elect Informat & Elect Engn, Dalian 116024, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China
Recommended Citation
GB/T 7714
Liu, Shenglan,Feng, Lin,Liu, Yang,et al. Manifold Warp Segmentation of Human Action[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(5):1414-1426.
APA Liu, Shenglan,Feng, Lin,Liu, Yang,Qiao, Hong,Wu, Jun,&Wang, Wei.(2018).Manifold Warp Segmentation of Human Action.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(5),1414-1426.
MLA Liu, Shenglan,et al."Manifold Warp Segmentation of Human Action".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.5(2018):1414-1426.
Files in This Item: Download All
File Name/Size DocType Version Access License
Manifold Warp Segmen(3667KB)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
[Liu, Shenglan]'s Articles
[Feng, Lin]'s Articles
[Liu, Yang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu, Shenglan]'s Articles
[Feng, Lin]'s Articles
[Liu, Yang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu, Shenglan]'s Articles
[Feng, Lin]'s Articles
[Liu, Yang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Manifold Warp Segmentation of Human 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.