| 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 Publication | Proceedings - 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 |
| Pages | 596-602 |
| 2018-12-04 | |
| Language | 英语 |
| DOI | 10.1109/SmartWorld.2018.00123 |
| Indexed By | Ei |
| EI Accession Number | 20190406418461 |
| Subtype | C |
| Abstract | Video 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. |
| Keyword | Big data Convolution Indexing (of information) Network security Neural networks Optical flows Security systems Smart city Trusted computing |
| EI Keywords | Big data ; Convolution ; Indexing (of information) ; Network security ; Neural networks ; Optical flows ; Security systems ; Smart city ; Trusted computing |
| Conference Name | 4th 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 Date | October 7, 2018 - October 11, 2018 |
| Conference Place | Guangzhou, China |
| EI Classification Number | 716.1 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 |
| Identifier | http://ir.ioe.ac.cn/handle/181551/9125 |
| Collection | 光电测控技术研究室（三室） |
| Affiliation | 1.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-SA | Application Full Text | ||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment