Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification
作者：
Highlights：
• We exploit different feature representations to improve person re-identification.
• Fusion of handcrafted and deep features enhances re-identification performance.
• Ranking aggregation improves re-identification performance.
摘要
•We exploit different feature representations to improve person re-identification.•Fusion of handcrafted and deep features enhances re-identification performance.•Ranking aggregation improves re-identification performance.
论文关键词：Person re-identification,Similarity learning,Feature fusion,Post-ranking,Ranking aggregation
论文评审过程：Received 8 October 2017, Revised 11 April 2018, Accepted 13 August 2018, Available online 16 September 2018, Version of Record 4 October 2018.
论文官网地址：https://doi.org/10.1016/j.imavis.2018.08.001
