Appearance feature enhancement for person re-identification

作者：

Highlights：

• A Pose-Invariant Convolutional Baseline is proposed.

• Appearance-Enhanced Feature Learning Network is proposed.

• The state-of-the-art results are reported in three Re-ID datasets.

摘要

•A Pose-Invariant Convolutional Baseline is proposed.•Appearance-Enhanced Feature Learning Network is proposed.•The state-of-the-art results are reported in three Re-ID datasets.

论文关键词：Person re-identification,Pose variation,Pose-Invariant Convolutional Baseline,Appearance-Enhanced Feature Learning Network

论文评审过程：Received 22 August 2019, Revised 11 July 2020, Accepted 16 July 2020, Available online 26 July 2020, Version of Record 6 August 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113771