Jointly learning compact multi-view hash codes for few-shot FKP recognition

作者：

Highlights：

• lWe propose a joint multi-view feature learning method for FKP recognition.lWe form multi-view data vectors (MVDVs) to precisely describe a FKP image.lWe jointly learn the compact hash codes of MVDVs in an unsupervised manner.lThe JLCMHC method achieves promising performance for few-shot FKP recognition.

摘要

lWe propose a joint multi-view feature learning method for FKP recognition.lWe form multi-view data vectors (MVDVs) to precisely describe a FKP image.lWe jointly learn the compact hash codes of MVDVs in an unsupervised manner.lThe JLCMHC method achieves promising performance for few-shot FKP recognition.

论文关键词：FKP biometrics,Multi-view features jointly learning,Few-show learning,Compact FKP descriptor

论文评审过程：Received 15 October 2019, Revised 31 October 2020, Accepted 11 February 2021, Available online 13 February 2021, Version of Record 19 February 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107894