Joint dictionary and metric learning for person re-identification

作者：

Highlights：

• A joint dictionary learning and metric learning algorithm is proposed.

• Closed-form solutions are proposed for updating the dictionary and coefficients.

• Hard negative weighting is utilized to alleviate amount bias.

• Cross datasets results validate the generalization ability of the algorithm.

摘要

•A joint dictionary learning and metric learning algorithm is proposed.•Closed-form solutions are proposed for updating the dictionary and coefficients.•Hard negative weighting is utilized to alleviate amount bias.•Cross datasets results validate the generalization ability of the algorithm.

论文关键词：Person re-identification,Dictionary learning,Metric learning,Hard negative mining

论文评审过程：Received 14 November 2016, Revised 10 June 2017, Accepted 25 June 2017, Available online 28 June 2017, Version of Record 27 July 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.06.026