中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 光电技术研究所
  3. 中国科学院光电技术研究所
  4. 光电探测技术研究室（三室）
A review of Convolutional-Neural-Network-based action recognition

文献类型：期刊论文

作者Yao, Guangle1,2,3; Lei, Tao2; Zhong, Jiandan1,2,3
刊名Pattern Recognition Letters
出版日期2019-02-01
卷号118页码:14-22
关键词Action recognition Deep learning Convolutional Neural Network Action representation
ISSN号0167-8655
DOI10.1016/j.patrec.2018.05.018
文献子类期刊论文
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 learning of deep information using Convolutional Neural Network (CNN). This motivated us to review the notable CNN-based action recognition works. Because CNN is primarily designed to extract 2D spatial features from still image and videos are naturally viewed as 3D spatiotemporal signals, the core issue of extending the CNN from image to video is temporal information exploitation. We divide the solutions for exploiting temporal information exploration into three strategies: 1) 3D CNN; 2) taking the motion-related information as the CNN input; and 3) fusion. In this paper, we present a comprehensive review of the CNN-based action recognition methods according to these strategies. We also discuss the action recognition performance on recent large-scale benchmarks and the limitations and future research directions of CNN-based action recognition. This paper offers an objective and clear review of CNN-based action recognition and provides a guide for future research. © 2018 Elsevier B.V.
WOS研究方向Computer Science, Artificial Intelligence
语种英语
WOS记录号WOS:000457976400003
出版者Elsevier B.V.
源URL[http://ir.ioe.ac.cn/handle/181551/9787]  
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.University of Electronic Science and Technology of China, No.4, Section 2, North Jianshe Road, Chengdu; 610054, China;
2.Institute of Optics and Electronics, Chinese Academy of Sciences, P.O. Box 350, Shuangliu, Chengdu; 610209, China;
3.University of Chinese Academy of Sciences, 19 A Yuquan Rd, Shijingshan District, Beijing; 100039, China
推荐引用方式
GB/T 7714		 Yao, Guangle,Lei, Tao,Zhong, Jiandan. A review of Convolutional-Neural-Network-based action recognition[J]. Pattern Recognition Letters,2019,118:14-22.
APA Yao, Guangle,Lei, Tao,&Zhong, Jiandan.(2019).A review of Convolutional-Neural-Network-based action recognition.Pattern Recognition Letters,118,14-22.
MLA Yao, Guangle,et al."A review of Convolutional-Neural-Network-based action recognition".Pattern Recognition Letters 118(2019):14-22.

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。