Convolutional covariance features: Conception, integration and performance in person re-identification

作者：

Highlights：

• Novel convolutional covariance features (CCF).

• Integration of CCF and flat features extracted in a hybrid deep network.

• Performance analysis against 18 state-of-the-art methods in person reidentification.

摘要

Highlights•Novel convolutional covariance features (CCF).•Integration of CCF and flat features extracted in a hybrid deep network.•Performance analysis against 18 state-of-the-art methods in person reidentification.

论文关键词：Person re-identification,Covariance features,Deep leaning,Transfer learning

论文评审过程：Received 31 January 2016, Revised 31 May 2016, Accepted 7 July 2016, Available online 9 July 2016, Version of Record 13 October 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.07.013