IOE OpenIR  > 光电测控技术研究室(三室)
Department光电测控技术研究室(三室)
Constructing hierarchical spatiotemporal information for action recognition
Yao, Guangle1,2,3; Zhong, Jiandan1,2,3; Lei, Tao1; Liu, Xianyuan1
Source PublicationProceedings - 2018 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovations, SmartWorld/UIC/ATC/ScalCom/CBDCom/IoP/SCI 2018
Pages596-602
2018-12-04
Language英语
DOI10.1109/SmartWorld.2018.00123
Indexed ByEi
EI Accession Number20190406418461
SubtypeC
AbstractVideo action recognition is widely applied in video indexing, intelligent surveillance, multimedia understanding, and other fields. Recently, it was greatly improved by incorporating the convolutional neural network (ConvNet). The features of shadow layers in ConvNet tend to model the apparent and motion of actions, and the features of deep layers tend to represent actions. In this paper, we propose to construct hierarchical information by combining the spatiotemporal features of shadow and deep layers in 3D ConvNet for action recognition. Specifically, we use Res3D to extract spatiotemporal information from different types of layers, and transfer the knowledge learned from RGB to optical flow field. We also propose a Parallel Pair Discriminant Correlation Analysis (PPDCA) to fuse the multiple layers' spatiotemporal information into a compact hierarchal action representation. The experimental results show that there is a good balance between accuracy and dimension in our proposed hierarchical spatiotemporal information, and our method not only outperforms the single layer Res3D methods but also achieves recognition performance comparable to that of state-of-the-art methods. © 2018 IEEE.
KeywordBig data Convolution Indexing (of information) Network security Neural networks Optical flows Security systems Smart city Trusted computing
EI KeywordsBig data ; Convolution ; Indexing (of information) ; Network security ; Neural networks ; Optical flows ; Security systems ; Smart city ; Trusted computing
Conference Name4th IEEE SmartWorld, 15th IEEE International Conference on Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovations, SmartWorld/UIC/ATC/ScalCom/CBDCom/IoP/SCI 2018
Conference DateOctober 7, 2018 - October 11, 2018
Conference PlaceGuangzhou, China
EI Classification Number716.1 Information Theory and Signal Processing ; 723 Computer Software, Data Handling and Applications ; 741.1 Light/Optics ; 903.1 Information Sources and Analysis ; 914.1 Accidents and Accident Prevention
Citation statistics
Document Type会议论文
Identifierhttp://ir.ioe.ac.cn/handle/181551/9125
Collection光电测控技术研究室(三室)
Affiliation1.Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China;
2.University of Electronic Science and Technology of China, Chengdu, China;
3.University of Chinese Academy of Sciences, Beijing, China
Recommended Citation
GB/T 7714
Yao, Guangle,Zhong, Jiandan,Lei, Tao,et al. Constructing hierarchical spatiotemporal information for action recognition[C],2018:596-602.
Files in This Item:
File Name/Size DocType Version Access License
2018-2149.pdf(536KB)会议论文 开放获取CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yao, Guangle]'s Articles
[Zhong, Jiandan]'s Articles
[Lei, Tao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yao, Guangle]'s Articles
[Zhong, Jiandan]'s Articles
[Lei, Tao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yao, Guangle]'s Articles
[Zhong, Jiandan]'s Articles
[Lei, Tao]'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.