An efficient framework for visible–infrared cross modality person re-identification

作者：

Highlights：

• A novel framework is proposed for visible–infrared cross modality re-identification.

• Complementary features are obtained from different representations of images.

• The framework improves state-of-the-art on SYSU-MM01 and RegDB with large margin.

摘要

•A novel framework is proposed for visible–infrared cross modality re-identification.•Complementary features are obtained from different representations of images.•The framework improves state-of-the-art on SYSU-MM01 and RegDB with large margin.

论文关键词：Person re-identification,Cross modality person re-identification,Local Zernike moments

论文评审过程：Received 4 June 2019, Revised 18 February 2020, Accepted 21 June 2020, Available online 29 June 2020, Version of Record 6 July 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115933