Equidistance constrained metric learning for person re-identification
作者：
Highlights：
• An equidistance constrained metric learning algorithm for person re-identification is proposed.
• In our method, points of the same class are collapsed into a single point, while points of different classes are mapped to different vertices of a regular simplex.
• Our method aims to guarantee the best separability of the training data, meanwhile, promote the generalization ability of the learned metric.
摘要
•An equidistance constrained metric learning algorithm for person re-identification is proposed.•In our method, points of the same class are collapsed into a single point, while points of different classes are mapped to different vertices of a regular simplex.•Our method aims to guarantee the best separability of the training data, meanwhile, promote the generalization ability of the learned metric.
论文关键词：Person re-identification,Metric learning,Equidistance embedding
论文评审过程：Received 1 July 2016, Revised 3 August 2017, Accepted 7 September 2017, Available online 9 September 2017, Version of Record 15 September 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.09.014
