Learning diverse and deep clues for person reidentification

作者：

Highlights：

• An efficient framework is used to handle both historic ReID and occluded ReID.

• Exploring diverse local features through the width channel attention.

• Constructing global context-aware features with pyramid attention.

• Enhancing the adaptability of the attention weights.

摘要

•An efficient framework is used to handle both historic ReID and occluded ReID.•Exploring diverse local features through the width channel attention.•Constructing global context-aware features with pyramid attention.•Enhancing the adaptability of the attention weights.

论文关键词：Attention network, convolutional neural network,Grouped pyramid,Global feature,Local features,Person re-identification

论文评审过程：Received 13 July 2022, Revised 22 August 2022, Accepted 26 August 2022, Available online 8 September 2022, Version of Record 19 September 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104551