Cross-modal prototype learning for zero-shot handwritten character recognition

作者：

Highlights：

• We extend the cross-modal prototype learning CMPL framework to three modalities.

• CMPL achieves state-of-the-art results on online and offline zero-shot handwritten character recognition.

• CMPL shows promising cross-domain generalization ability in zero-shot handwritten character recognition.

摘要

•We extend the cross-modal prototype learning CMPL framework to three modalities.•CMPL achieves state-of-the-art results on online and offline zero-shot handwritten character recognition.•CMPL shows promising cross-domain generalization ability in zero-shot handwritten character recognition.

论文关键词：Online handwriting,Offline handwriting,Printed character,Zero-shot,Prototype,Cross-modality

论文评审过程：Received 23 February 2021, Revised 7 June 2022, Accepted 16 June 2022, Available online 17 June 2022, Version of Record 30 June 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108859