Improved person re-identification based on saliency and semantic parsing with deep neural network models

作者：

Highlights：

• Development of a novel framework for person re-identification based on saliency and semantic parsing

• Fusion of multiple clues to guide a backbone convolutional neural network

• Evaluation on challenging public data sets

• Results superior/comparable to the literature

摘要

•Development of a novel framework for person re-identification based on saliency and semantic parsing•Fusion of multiple clues to guide a backbone convolutional neural network•Evaluation on challenging public data sets•Results superior/comparable to the literature

论文关键词：Person re-identification,Deep learning,Multi-clue guided learning,Human semantic parsing,Saliency detection,Convolutional neural networks

论文评审过程：Received 15 July 2018, Revised 12 December 2018, Accepted 16 July 2019, Available online 13 September 2019, Version of Record 2 November 2019.

论文官网地址：https://doi.org/10.1016/j.imavis.2019.07.009