Constructing hierarchical spatiotemporal information for action recognition
文献类型：会议论文
| 作者 | Yao, Guangle1,2,3; Zhong, Jiandan1,2,3; Lei, Tao1; Liu, Xianyuan1 |
| 出版日期 | 2018-12-04 |
| 会议日期 | October 7, 2018 - October 11, 2018 |
| 会议地点 | Guangzhou, China |
| 关键词 | Big data Convolution Indexing (of information) Network security Neural networks Optical flows Security systems Smart city Trusted computing |
| DOI | 10.1109/SmartWorld.2018.00123 |
| 页码 | 596-602 |
| 英文摘要 | 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. |
| 会议录 | 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
 |
| 文献子类 | C |
| 语种 | 英语 |
| 源URL | [http://ir.ioe.ac.cn/handle/181551/9125]  |
| 专题 | 光电技术研究所_光电探测技术研究室（三室） |
| 作者单位 | 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 |
| 推荐引用方式 GB/T 7714 | Yao, Guangle,Zhong, Jiandan,Lei, Tao,et al. Constructing hierarchical spatiotemporal information for action recognition[C]. 见:. Guangzhou, China. October 7, 2018 - October 11, 2018. |
入库方式： OAI收割
来源：光电技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。