OPT OpenIR  > 光学影像学习与分析中心
Action recognition using spatial-optical data organization and sequential learning framework
Yuan, Yuan1; Zhao, Yang1,2; Wang, Qi3,4
Department光学影像学习与分析中心
2018-11-13
Source PublicationNEUROCOMPUTING
ISSN0925-2312;1872-8286
Volume315Pages:221-233
Contribution Rank1
Abstract

Recognizing human actions in videos is a challenging problem owning to complex motion appearance, various backgrounds and semantic gap between low-level features and high-level semantics. Existing methods have scored some achievements and many new thoughts have been proposed for action recognition. They focus on designing a robust feature description and training an elaborate learning model, and many of them can benefit from a two-stream network with a stack of RGB frames and optical flow frames. However, these features for human action representation are struggling with the limited feature representation as RGB videos are confused by static appearance redundancy and optical flow videos cannot represent the detailed appearance. To solve these problems, we propose an efficient algorithm based on the spatial-optical data organization and the sequential learning framework. There are two contributions of our method: a novel data organization based on hierarchical weighting segmentation and optical flow for video representation, and a lightweight deep learning model based on the Convolutional 3D (C3D) network and the Recurrent Neural Network (RNN) for complicated action recognition. The new data organization aggregates the merits of motion appearance, movement trajectories and optical flow in a creative way to highlight the meaningful information. And the proposed lightweight model has an insight into patterns and semantics of sequential data by low-level spatiotemporal feature extraction and high-level information mining. The proposed method is evaluated on the state-of-the-art dataset and the results demonstrate that our method have a good performance for complex human action recognition. (c) 2018 Elsevier B.V. All rights reserved.

KeywordAction Recognition Spatiotemporal Feature Deep Learning Sequential Learning Framework
DOI10.1016/j.neucom.2018.06.071
Indexed BySCI ; EI
Language英语
WOS IDWOS:000445934400022
PublisherELSEVIER SCIENCE BV
EI Accession Number20183005605340
Citation statistics
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/30659
Collection光学影像学习与分析中心
Corresponding AuthorWang, Qi
Affiliation1.Chinese Acad Sci, Ctr Opt IMagery Anal & Learning OPTIMAL, Xian Inst Opt & Precis Mech, Xian 710119, Shaanxi, Peoples R China
2.Univ Chinese Acad Sci, Beijing 049, Peoples R China
3.Northwestern Polytech Univ, Sch Comp Sci, Ctr Opt IMagery Anal & Learning OPTIMAL, Xian 710072, Shaanxi, Peoples R China
4.Northwestern Polytech Univ, Unmanned Syst Res Inst, Xian 710072, Shaanxi, Peoples R China
Recommended Citation
GB/T 7714
Yuan, Yuan,Zhao, Yang,Wang, Qi. Action recognition using spatial-optical data organization and sequential learning framework[J]. NEUROCOMPUTING,2018,315:221-233.
APA Yuan, Yuan,Zhao, Yang,&Wang, Qi.(2018).Action recognition using spatial-optical data organization and sequential learning framework.NEUROCOMPUTING,315,221-233.
MLA Yuan, Yuan,et al."Action recognition using spatial-optical data organization and sequential learning framework".NEUROCOMPUTING 315(2018):221-233.
Files in This Item:
File Name/Size DocType Version Access License
Action recognition u(2476KB)期刊论文出版稿开放获取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
[Yuan, Yuan]'s Articles
[Zhao, Yang]'s Articles
[Wang, Qi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yuan, Yuan]'s Articles
[Zhao, Yang]'s Articles
[Wang, Qi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yuan, Yuan]'s Articles
[Zhao, Yang]'s Articles
[Wang, Qi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Action recognition using spatial-optical data organization and sequential learning framework.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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