Attention-aware scoring learning for person re-identification

作者：

Highlights：

• An Attention-Aware Scoring Learning (AASL) framework is proposed.

• Spatial Attention Grid and Channel Attention Grid are proposed as attention modules.

• Score learning head is explored to optimize the parameters of attention modules.

• Extensive experiments show that our method obtains a competitive performance compared with other state-of-the-art re-identification algorithms.

摘要

•An Attention-Aware Scoring Learning (AASL) framework is proposed.•Spatial Attention Grid and Channel Attention Grid are proposed as attention modules.•Score learning head is explored to optimize the parameters of attention modules.•Extensive experiments show that our method obtains a competitive performance compared with other state-of-the-art re-identification algorithms.

论文关键词：Person re-identification,Attention module,Score learning head

论文评审过程：Received 18 March 2020, Revised 4 June 2020, Accepted 15 June 2020, Available online 20 June 2020, Version of Record 20 June 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.106154