Leader-Based Multi-Scale Attention Deep Architecture for Person Re-Identification

Leader-Based Multi-Scale Attention Deep Architecture for Person Re-Identification
复制标题

基于领导者的多尺度注意力深度架构,用于行人重识别

DOI:
10.1109/tpami.2019.2928294
复制
发表时间:
2020-02
影响因子:
23.6
通讯作者:
Xiangyang Xue
Xiangyang Xue
中科院分区:
计算机科学1区
文献类型:
--
作者:
Xuelin Qian;Yanwei Fu;Tao Xiang;Yu-Gang Jiang;Xiangyang Xue

文献摘要

参考文献

被引文献

相似文献

个人再识别(Re-id)的目的是在公共空间中匹配不重叠的摄像头视角中的人。这是一个具有挑战性的问题,因为监控视频中捕捉到的人经常穿着相似的衣服。因此,它们在外观上的差异通常是微妙的,只有在特定的位置和规模才能检测到。在本文中,我们提出了一种深度Re-id网络(MuDeep),它由两种新颖的层组成--多尺度深度学习层和基于领导者的注意学习层。具体地说,前者学习不同尺度上的深度区分特征表示,而后者利用来自多个尺度的信息来引导和确定每个尺度的最优权重。不同空间位置对提取区分性特征的重要性通过基于领导者的注意学习层被明确地学习。实验结果表明,该算法在多个性能指标上均优于同类算法,并且在领域泛化环境下具有更好的泛化能力。
Person re-identification (re-id) aims to match people across non-overlapping camera views in a public space. This is a challenging problem because the people captured in surveillance videos often wear similar clothing. Consequently, the differences in their appearance are typically subtle and only detectable at particular locations and scales. In this paper, we propose a deep re-id network (MuDeep) that is composed of two novel types of layers – a multi-scale deep learning layer, and a leader-based attention learning layer. Specifically, the former learns deep discriminative feature representations at different scales, while the latter utilizes the information from multiple scales to lead and determine the optimal weightings for each scale. The importance of different spatial locations for extracting discriminative features is learned explicitly via our leader-based attention learning layer. Extensive experiments are carried out to demonstrate that the proposed MuDeep outperforms the state-of-the-art on a number of benchmarks and has a better generalization ability under a domain generalization setting.
DOI: 10.1109/icdsc.2007.4357522
发表时间: 2007-09
期刊: 2007 First ACM/IEEE International Conference on Distributed Smart Cameras
影响因子: --
作者:
Thomas Mensink;W. Zajdel;B. Kröse
通讯作者: Thomas Mensink;W. Zajdel;B. Kröse
DOI: --
发表时间: 2017-03
期刊: ArXiv
影响因子: --
作者:
Alexander Hermans;Lucas Beyer;B. Leibe
通讯作者: Alexander Hermans;Lucas Beyer;B. Leibe
DOI: 10.1109/cvpr.2016.152
发表时间: 2016-06
期刊: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子: --
作者:
Tetsu Matsukawa;Takahiro Okabe;Einoshin Suzuki;Yoichi Sato
通讯作者: Tetsu Matsukawa;Takahiro Okabe;Einoshin Suzuki;Yoichi Sato
DOI: 10.1145/2964284.2967209
发表时间: 2016-10
期刊: Proceedings of the 24th ACM international conference on Multimedia
影响因子: --
作者:
Jiawei Liu;Zhengjun Zha;Q. Tian;Dong Liu;Ting Yao;Q. Ling;Tao Mei
通讯作者: Jiawei Liu;Zhengjun Zha;Q. Tian;Dong Liu;Ting Yao;Q. Ling;Tao Mei
DOI: 10.1109/cvpr.2016.144
发表时间: 2016-06
期刊: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子: --
作者:
Faqiang Wang;W. Zuo;Liang Lin;D. Zhang;Lei Zhang
通讯作者: Faqiang Wang;W. Zuo;Liang Lin;D. Zhang;Lei Zhang