期刊
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
卷 -, 期 -, 页码 5409-5418出版社
IEEE
DOI: 10.1109/ICCV.2017.577
关键词
-
资金
- NSFC [U1611461, U1509206]
- STCSM [STCSM (#16JC1420401]
Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people captured in surveillance videos wear similar clothes. Consequently, the differences in their appearance are often subtle and only detectable at the right location and scales. Existing re-id models, particularly the recently proposed deep learning based ones match people at a single scale. In contrast, in this paper, a novel multi-scale deep learning model is proposed. Our model is able to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for matching. The importance of different spatial locations for extracting discriminative features is also learned explicitly. Experiments are carried out to demonstrate that the proposed model outperforms the state-of-the art on a number of benchmarks.
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