Structure alignment of attributes and visual features for cross-dataset person re-identification

作者：

Highlights：

• Self-reconstruction structure alignment is proposed for cross-domain person re-identification.

• Visual attribute are aligned by class prototype to promote discrimination of predicted attributes.

• A self-supervised learning framework is developed to alleviate the domain bias.

摘要

•Self-reconstruction structure alignment is proposed for cross-domain person re-identification.•Visual attribute are aligned by class prototype to promote discrimination of predicted attributes.•A self-supervised learning framework is developed to alleviate the domain bias.

论文关键词：Person re-identification,Self-supervised strategy,Domain adaptation,Structure alignment,Self-reconstruction

论文评审过程：Received 1 September 2019, Revised 22 April 2020, Accepted 29 April 2020, Available online 4 May 2020, Version of Record 11 May 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107414