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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能感知与计算研究中心
Frame-GAN: Increasing the frame rate of gait videos with generative adversarial networks

文献类型：期刊论文

作者Xue, Wei1,3; Ai, Hong3; Sun, Tianyu1; Song, Chunfeng1,2; Huang, Yan1,2; Wang, Liang1,2
刊名NEUROCOMPUTING
出版日期2020-03-07
卷号380页码:95-104
ISSN号0925-2312
关键词Gait recognition Generative adversarial networks Metric learning Deep learning
DOI10.1016/j.neucom.2019.11.015
通讯作者Ai, Hong(aihong@hrbust.edu.cn)
英文摘要Most existing methods of identifying person except gait recognition require the cooperation of the subjects. Aiming at detecting the pattern of human walking movement, gait recognition takes advantage of the time-serial data and can identify a person distantly. The time-serial data, which is usually presented in video form, always has a limitation in frame rate, which intrinsically affects the performance of the recognition models. In order to increase the frame rate of gait videos, we propose a new kind of generative adversarial networks (GAN) named Frame-GAN to reduce the gap between adjacent frames. Inspired by the recent advances in metric learning, we also propose a new effective loss function named Margin Ratio Loss (MRL) to boost the recognition model. We evaluate the proposed method on the challenging CASIA-B and OU-ISIR gait databases. Extensive experimental results show that the proposed Frame-GAN and MRL are effective. (C) 2019 Elsevier B.V. All rights reserved.
WOS关键词RECOGNITION ; IMAGE
资助项目National Key Research and Development Program of China[2016YFB1001000] ; National Natural Science Foundation of China[61525306] ; National Natural Science Foundation of China[61633021] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61420106015] ; National Natural Science Foundation of China[61806194] ; Capital Science and Technology Leading Talent Training Project[Z181100006318030] ; Beijing Science and Technology Project[Z181100008918010] ; NVIDIA ; NVIDIA DGX-1 AI Supercomputer ; CAS-AIR
WOS研究方向Computer Science
语种英语
出版者ELSEVIER
WOS记录号WOS:000507986500010
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Capital Science and Technology Leading Talent Training Project ; Beijing Science and Technology Project ; NVIDIA ; NVIDIA DGX-1 AI Supercomputer ; CAS-AIR
源URL[http://ir.ia.ac.cn/handle/173211/29541]  
专题自动化研究所_智能感知与计算研究中心
通讯作者Ai, Hong
作者单位1.Chinese Acad Sci CASIA, CRIPAC, Inst Automat, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China
2.UCAS, Beijing 100190, Peoples R China
3.Harbin Univ Sci & Technol, Sch Automat, Harbin 150001, Peoples R China
推荐引用方式
GB/T 7714		 Xue, Wei,Ai, Hong,Sun, Tianyu,et al. Frame-GAN: Increasing the frame rate of gait videos with generative adversarial networks[J]. NEUROCOMPUTING,2020,380:95-104.
APA Xue, Wei,Ai, Hong,Sun, Tianyu,Song, Chunfeng,Huang, Yan,&Wang, Liang.(2020).Frame-GAN: Increasing the frame rate of gait videos with generative adversarial networks.NEUROCOMPUTING,380,95-104.
MLA Xue, Wei,et al."Frame-GAN: Increasing the frame rate of gait videos with generative adversarial networks".NEUROCOMPUTING 380(2020):95-104.

入库方式： OAI收割

来源：自动化研究所

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。