Deep ranking model by large adaptive margin learning for person re-identification

作者：

Highlights：

• A novel distance metric aiming at preserving a large adaptive margin, which is more appropriate for dynamic feature space, is proposed.

• A novel part-based deep architecture is build to extract the discriminative feature representation of different body parts.

• The final results outperform the state-of-the-art methods on all the four challenging benchmark datasets.

摘要

•A novel distance metric aiming at preserving a large adaptive margin, which is more appropriate for dynamic feature space, is proposed.•A novel part-based deep architecture is build to extract the discriminative feature representation of different body parts.•The final results outperform the state-of-the-art methods on all the four challenging benchmark datasets.

论文关键词：Person re-identification,Deep ranking model,Metric learning

论文评审过程：Received 25 March 2017, Revised 16 August 2017, Accepted 13 September 2017, Available online 19 September 2017, Version of Record 23 October 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.09.024