AlignedReID++: Dynamically matching local information for person re-identification

作者：

Highlights：

• We porpose a new method name DMLI that can dynamically match horizontal stripes without requiring extra supervision or explicit pose estimation.

• We introduce a local branch based on DMLI and design a novel framework called AlignedReID++, which can guide the global branch to learn more discriminative global features.

• Experimental results demonstrate that the proposed approach achieves competitive results in both rank-1 accuracy and mAP on Market1501, DukeMTMCReID, CUHK03 and MSMT17 databases.

摘要

•We porpose a new method name DMLI that can dynamically match horizontal stripes without requiring extra supervision or explicit pose estimation.•We introduce a local branch based on DMLI and design a novel framework called AlignedReID++, which can guide the global branch to learn more discriminative global features.•Experimental results demonstrate that the proposed approach achieves competitive results in both rank-1 accuracy and mAP on Market1501, DukeMTMCReID, CUHK03 and MSMT17 databases.

论文关键词：Person re-identification,CNNs,Dynamically alignment

论文评审过程：Received 19 July 2018, Revised 18 April 2019, Accepted 15 May 2019, Available online 16 May 2019, Version of Record 20 May 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.05.028