Feature Aggregation With Reinforcement Learning for Video-Based Person Re-Identification

Feature Aggregation With Reinforcement Learning for Video-Based Person Re-Identification
复制标题

基于视频的行人重新识别的强化学习特征聚合

DOI:
10.1109/tnnls.2019.2899588
复制
发表时间:
2019-03
期刊:
IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
影响因子:
--
通讯作者:
Li Yibin
Li Yibin
中科院分区:
其他
文献类型:
--
作者:
Zhang Wei;He Xuanyu;Lu Weizhi;Qiao Hong;Li Yibin

文献摘要

参考文献

被引文献

相似文献

基于视频的人员重新识别(Re-id)匹配来自不同摄像机的两个人的轨迹。从序列图像中提取特征,然后聚合为轨迹特征。与已有的通过简单平均帧特征或使用递归神经网络等时态模型进行特征聚合的工作相比,本文提出了一种基于强化学习的智能特征聚合方法。具体地说,我们训练一个代理来确定序列中的哪些帧应该在聚合中被丢弃,这可以被视为一个决策过程。通过这种方法,该方法避免了引入序列的噪声信息,并在生成跟踪特征时保留了这些有价值的帧。在基准数据集上的实验结果表明,在现有模型的基础上,我们的方法可以明显提高Re-id的准确率。
Video-based person re-identification (re-id) matches two tracks of persons from different cameras. Features are extracted from the images of a sequence and then aggregated as a track feature. Compared to existing works that aggregate frame features by simply averaging them or using temporal models such as recurrent neural networks, we propose an intelligent feature aggregate method based on reinforcement learning. Specifically, we train an agent to determine which frames in the sequence should be abandoned in the aggregation, which can be treated as a decision making process. By this way, the proposed method avoids introducing noisy information of the sequence and retains these valuable frames when generating a track feature. On benchmark data sets, experimental results show that our method can boost the re-id accuracy obviously based on the state-of-the-art models.
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: --
发表时间: 2015-07
期刊: --
影响因子: --
作者:
Sheng Li;Ming Shao;Y. Fu
通讯作者: Sheng Li;Ming Shao;Y. Fu
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
DOI: 10.1007/978-3-319-46466-4_52
发表时间: 2016-10
期刊: --
影响因子: --
作者:
Liang Zheng;Zhi Bie;Yifan Sun;Jingdong Wang;Chi Su;Shengjin Wang;Q. Tian
通讯作者: Liang Zheng;Zhi Bie;Yifan Sun;Jingdong Wang;Chi Su;Shengjin Wang;Q. Tian
DOI: 10.1109/cvpr.2018.00709
发表时间: 2017-12
期刊: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Jianfu Zhang;Naiyan Wang;Liqing Zhang
通讯作者: Jianfu Zhang;Naiyan Wang;Liqing Zhang