CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Hierarchical Nonlinear Orthogonal Adaptive-Subspace Self-Organizing Map based Feature Extraction for Human Action Recognition
Du, Yang1,2,3; Yuan, Chunfeng1; Hu, Weiming1; Yang, Hao1,2,3
2018
Conference NameAAAI Conference on Artificial Intelligence (AAAI)
Source Publication2018 AAAI Conference on Artificial Intelligence
Conference Date20180202-20180207
Conference PlaceNew Orleans, Louisiana, USA
Abstract
Feature extraction is a critical step in the task of action recognition. Hand-crafted features are often restricted because of their fixed forms and deep learning features are more effective but need large-scale labeled data for training. In this paper, we propose a new hierarchical Nonlinear Orthogonal Adaptive-Subspace Self-Organizing Map (NOASSOM) to
adaptively and learn effective features from data without supervision. NOASSOM is extended from Adaptive-Subspace Self-Organizing Map (ASSOM) which only deals with linear data and is trained with supervision by the labeled data. Firstly, by adding a nonlinear orthogonal map layer, NOASSOM is able to handle the nonlinear input data and it avoids defining the specific form of the nonlinear orthogonal map by a kernel trick. Secondly, we modify loss function of ASSOM such that every input sample is used to train model individually. In this way, NOASSOM effectively learns the statistic patterns from data without supervision. Thirdly, we propose a hierarchical NOASSOM to extract more representative
features. Finally, we apply the proposed hierarchical NOASSOM
to efficiently describe the appearance and motion information
around trajectories for action recognition. Experimental
results on widely used datasets show that our method has
superior performance than many state-of-the-art hand-crafted
features and deep learning features based methods.
KeywordAction Recognition Feature Extraction
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19734
Collection模式识别国家重点实验室_视频内容安全
Corresponding AuthorYuan, Chunfeng
Affiliation1.CAS Center for Excellence in Brain Science and Intelligence Technology, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.MTdata, Meitu
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Du, Yang,Yuan, Chunfeng,Hu, Weiming,et al. Hierarchical Nonlinear Orthogonal Adaptive-Subspace Self-Organizing Map based Feature Extraction for Human Action Recognition[C],2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
Du_Hierarchical Nonl(4323KB)会议论文 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
[Du, Yang]'s Articles
[Yuan, Chunfeng]'s Articles
[Hu, Weiming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Du, Yang]'s Articles
[Yuan, Chunfeng]'s Articles
[Hu, Weiming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Du, Yang]'s Articles
[Yuan, Chunfeng]'s Articles
[Hu, Weiming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Du_Hierarchical Nonlinear Orthogonal Adaptive-Subspace Self-Organizing Map_AAAI_2018.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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