Zero-shot face recognition: Improving the discriminability of visual face features using a Semantic-Guided Attention Model

作者：

Highlights：

• An attention-based method for improving the performance of zero-shot face recognition.

• Derivation of Attribute Attention Maps (AAM) for the most salient image attributes.

• Extensive visual analysis of the AAM obtained from both CelebA and ZSL datasets.

摘要

•An attention-based method for improving the performance of zero-shot face recognition.•Derivation of Attribute Attention Maps (AAM) for the most salient image attributes.•Extensive visual analysis of the AAM obtained from both CelebA and ZSL datasets.

论文关键词：Face recognition,Zero-shot learning,Attention-based models

论文评审过程：Received 10 February 2022, Revised 16 July 2022, Accepted 17 August 2022, Available online 24 August 2022, Version of Record 31 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118635