An extended attention mechanism for scene text recognition

作者：

Highlights：

• An extended attention mechanism is designed to recognize scene texts.

• Attention on Attention(AoA) is applied in the Encoder and Decoder modules.

• The method outperforms seven benchmarks by 4.5% averagely over 10 datasets.

摘要

•An extended attention mechanism is designed to recognize scene texts.•Attention on Attention(AoA) is applied in the Encoder and Decoder modules.•The method outperforms seven benchmarks by 4.5% averagely over 10 datasets.

论文关键词：Scene text recognition,Attention on attention,Deep neural network,Encoder–decoder framework

论文评审过程：Received 10 September 2021, Revised 23 January 2022, Accepted 25 April 2022, Available online 11 May 2022, Version of Record 14 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117377