期刊
MULTIMEDIA TOOLS AND APPLICATIONS
卷 80, 期 19, 页码 29129-29138出版社
SPRINGER
DOI: 10.1007/s11042-021-11127-0
关键词
Person re-identification; Graph convolution
类别
资金
- Chung-Ang University Graduate Research Scholarship Grants in 2018
- National Research Foundation of Korea (NRF) - Korea government(MSIT) [NRF-2020R1C1C1004907]
The research combines graph convolution network with traditional triplet loss methods to adjust the mutual distance between different features through learning, effectively improving the re-identification methods.
Person re-identification (re-id) aims to identity the same person over multiple cameras; it has been successfully applied to various computer vision applications as a fundamental method. Owing to the development of deep learning, person re-id methods, which typically use triplet networks based on triplet loss, have demonstrated great success. However, the appearances of people are similar and hence difficult to distinguish in many cases. Therefore, we present a novel graph convolution network and enhances traditional triplet loss functions. Our method defines reference, positive, and negative features for triplet loss as three vertices of a graph, respectively, and adjusts their mutual distance through learning. The method adopts graph convolutions efficiently, thereby affording low computational costs. Experimental results demonstrate that our method is superior to the baseline on the Market-1501 dataset. The proposed GCN-based triplet loss considerably contributes to improve re-identification methods quantitatively and qualitatively.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据