IRANet: Identity-relevance aware representation for cloth-changing person re-identification

作者:

Highlights:

• The IRANet is proposed to address cloth-changing person re-identification task.

• A more reliable cue is introduced by mining the identity information from head.

• A human head detection module is designed to localize the human head area.

• A head-guided attention module is used to highlight the head embedding.

• The proposed method achieves higher matching rates than the competing methods.

摘要

Highlights•The IRANet is proposed to address cloth-changing person re-identification task.•A more reliable cue is introduced by mining the identity information from head.•A human head detection module is designed to localize the human head area.•A head-guided attention module is used to highlight the head embedding.•The proposed method achieves higher matching rates than the competing methods.

论文关键词:Cloth-changing person re-identification,Identity-relevance,Feature representation

论文评审过程:Received 19 July 2021, Revised 27 October 2021, Accepted 1 November 2021, Available online 6 November 2021, Version of Record 27 November 2021.

论文官网地址:https://doi.org/10.1016/j.imavis.2021.104335