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. 人工智能与机器学习
Tensor Multi-Task Learning for Person Re-Identification

文献类型：期刊论文

作者Zhang, Zhizhong1,4; Xie, Yuan5; Zhang, Wensheng1,4; Tang, Yongqiang3; Tian, Qi2
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2020
卷号29页码:2463-2477
关键词Cameras Task analysis Measurement Visualization Training Computational modeling Person re-identification multi-task learning tensor optimization
ISSN号1057-7149
DOI10.1109/TIP.2019.2949929
通讯作者Zhang, Wensheng(zhangwenshengia@hotmail.com) ; Tian, Qi(tian.qi1@huawei.com)
英文摘要This article presents a tensor multi-task model for person re-identification (Re-ID). Due to discrepancy among cameras, our approach regards Re-ID from multiple cameras as different but related classification tasks, each task corresponding to a specific camera. In each task, we distinguish the person identity as a one-vs-all linear classification problem, where one classifier is associated with a specific person. By constructing all classifiers into a task-specific projection matrix, the proposed method could utilize all the matrices to form a tensor structure, and jointly train all the tasks in a uniform tensor space. In this space, by assuming the features of the same person under different cameras are generated from a latent subspace, and different identities under the same perspective share similar patterns, the high-order correlations, not only across different tasks but also within a certain task, can be captured by utilizing a new type of low-rank tensor constraint. Therefore, the learned classifiers transform the original feature vector into the latent space, where feature distributions across cameras can be well-aligned. Moreover, this model can be incorporated into multiple visual features to boost the performance, and easily extended to the unsupervised setting. Extensive experiments and comparisons with recent Re-ID methods manifest the competitive performance of our method.
资助项目National Key R&D Program of China[2017YFC0803700] ; National Natural Science Foundation of China[U1636220] ; National Natural Science Foundation of China[61432008] ; National Natural Science Foundation of China[61472423] ; National Natural Science Foundation of China[61772524] ; Beijing Municipal Natural Science Foundation[4182067] ; Fundamental Research Funds for the Central Universities ; Shanghai Key Laboratory of Trustworthy Computing
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000507869900020
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key R&D Program of China ; National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation ; Fundamental Research Funds for the Central Universities ; Shanghai Key Laboratory of Trustworthy Computing
源URL[http://ir.ia.ac.cn/handle/173211/29511]  
专题精密感知与控制研究中心_人工智能与机器学习
自动化研究所_精密感知与控制研究中心
通讯作者Zhang, Wensheng; Tian, Qi
作者单位1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China
2.Huawei Noahs Ark Lab, Comp Vis, Shenzhen 51800, Peoples R China
3.Chinese Acad Sci, Res Ctr Precis Sensing & Control, Inst Automat, Beijing 100190, Peoples R China
4.Chinese Acad Sci Ences, Res Ctr Precis Sensing & Control, Inst Automat, Beijing 100190, Peoples R China
5.East China Normal Univ, Sch Comp Sci & Technol, Shanghai 200241, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Zhizhong,Xie, Yuan,Zhang, Wensheng,et al. Tensor Multi-Task Learning for Person Re-Identification[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:2463-2477.
APA Zhang, Zhizhong,Xie, Yuan,Zhang, Wensheng,Tang, Yongqiang,&Tian, Qi.(2020).Tensor Multi-Task Learning for Person Re-Identification.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,2463-2477.
MLA Zhang, Zhizhong,et al."Tensor Multi-Task Learning for Person Re-Identification".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):2463-2477.

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。