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. 多模态人工智能系统全国重点实验室
  5. 生物识别与安全技术研究中心
Deep Hybrid Similarity Learning for Person Re-Identification

文献类型：期刊论文

作者Zhu JQ(朱建清); Huanqiang Zeng; Liao SC(廖胜才); Lei Z(雷震); Canhui Cai; Li Xin Zheng
刊名IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
出版日期2018-11-01
卷号28期号:11页码:3183-3193
关键词Metric learning convolution neural network deep hybrid similarity learning person re-identification (Re-ID)
ISSN号1051-8215
DOI10.1109/TCSVT.2017.2734740
通讯作者Zeng, Huanqiang(zeng0043@hqu.edu.cn)
英文摘要Person re-identification (Re-ID) aims to match person images captured from two non-overlapping cameras. In this paper, a deep hybrid similarity learning (DHSL) method for person Re-ID based on a convolution neural network (CNN) is proposed. In our approach, a light CNN learning feature pair for the input image pair is simultaneously extracted. Then, both the elementwise absolute difference and multiplication of the CNN learning feature pair are calculated. Finally, a hybrid similarity function is designed to measure the similarity between the feature pair, which is realized by learning a group of weight coefficients to project the elementwise absolute difference and multiplication into a similarity score. Consequently, the proposed DHSL method is able to reasonably assign complexities of feature learning and metric learning in a CNN, so that the performance of person Re-ID is improved. Experiments on three challenging person Re-ID databases, QMUL GRID, VIPeR, and CUHK03, illustrate that the proposed DHSL method is superior to multiple state-of-the-art person Re-ID methods.
WOS关键词FEATURES ; VERIFICATION
资助项目National Natural Science Foundation of China[61602191] ; National Natural Science Foundation of China[61672521] ; National Natural Science Foundation of China[61375037] ; National Natural Science Foundation of China[61473291] ; National Natural Science Foundation of China[61572501] ; National Natural Science Foundation of China[61572536] ; National Natural Science Foundation of China[61502491] ; National Natural Science Foundation of China[61372107] ; National Natural Science Foundation of China[61401167] ; Natural Science Foundation of Fujian Province[2016J01308] ; Scientific and Technology Founds of Xiamen[3502Z20173045] ; Promotion Program for Young and Middleaged Teacher in Science and Technology Research of Huaqiao University[ZQN-PY418] ; Promotion Program for Young and Middleaged Teacher in Science and Technology Research of Huaqiao University[ZQN-YX403] ; Scientific Research Funds of Huaqiao University[16BS108]
WOS研究方向Engineering
语种英语
WOS记录号WOS:000449392100008
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China ; Natural Science Foundation of Fujian Province ; Scientific and Technology Founds of Xiamen ; Promotion Program for Young and Middleaged Teacher in Science and Technology Research of Huaqiao University ; Scientific Research Funds of Huaqiao University
源URL[http://ir.ia.ac.cn/handle/173211/20621]  
专题自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
推荐引用方式
GB/T 7714		 Zhu JQ,Huanqiang Zeng,Liao SC,et al. Deep Hybrid Similarity Learning for Person Re-Identification[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2018,28(11):3183-3193.
APA Zhu JQ,Huanqiang Zeng,Liao SC,Lei Z,Canhui Cai,&Li Xin Zheng.(2018).Deep Hybrid Similarity Learning for Person Re-Identification.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,28(11),3183-3193.
MLA Zhu JQ,et al."Deep Hybrid Similarity Learning for Person Re-Identification".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 28.11(2018):3183-3193.

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。