Attribute saliency network for person re-identification

作者：

Highlights：

• Attribute learning improves person re-identification task.

• Global, local and attribute networks allow discriminative representation encoding.

• Saliency maps are generated by combining various fine-grained local heatmaps.

• Attribute and identity learning provide visual and text-based image retrieval.

摘要

Highlights•Attribute learning improves person re-identification task.•Global, local and attribute networks allow discriminative representation encoding.•Saliency maps are generated by combining various fine-grained local heatmaps.•Attribute and identity learning provide visual and text-based image retrieval.

论文关键词：Person re-identification,Person attribute,Attention or saliency map,Attribute learning

论文评审过程：Received 15 March 2021, Revised 1 September 2021, Accepted 6 September 2021, Available online 10 September 2021, Version of Record 20 September 2021.

论文官网地址：https://doi.org/10.1016/j.imavis.2021.104298