Cross-scale global attention feature pyramid network for person search

作者：

Highlights：

• A multi-head global attention module is designed.

• Cross-scale global attention feature pyramid network is proposed

• An adaptive feature aggregation with attention layer is designed.

• 94.9% and 47.9% of mAP on CUHK-SYSU and PRW for person search.

摘要

•A multi-head global attention module is designed.•Cross-scale global attention feature pyramid network is proposed•An adaptive feature aggregation with attention layer is designed.•94.9% and 47.9% of mAP on CUHK-SYSU and PRW for person search.

论文关键词：Person search,Global attention,Feature pyramid network,Multi-scale,Fine-grained

论文评审过程：Received 17 June 2021, Revised 16 September 2021, Accepted 24 October 2021, Available online 28 October 2021, Version of Record 5 November 2021.

论文官网地址：https://doi.org/10.1016/j.imavis.2021.104332