Learning to disentangle scenes for person re-identification

作者：

Highlights：

• A divide-and-conquer strategy to deal with person re-identification.

• Knowledge sharing between different scenes.

• Capitalizing on the potentials of multi-branch networks.

• State-of-the-art performances on five person re-identification benchmarks.

摘要

•A divide-and-conquer strategy to deal with person re-identification.•Knowledge sharing between different scenes.•Capitalizing on the potentials of multi-branch networks.•State-of-the-art performances on five person re-identification benchmarks.

论文关键词：Person re-identification,Divide-and-conquer,Multi-branch network

论文评审过程：Received 18 April 2021, Revised 14 July 2021, Accepted 15 October 2021, Available online 23 October 2021, Version of Record 2 November 2021.

论文官网地址：https://doi.org/10.1016/j.imavis.2021.104330