Improving Handwritten Mathematical Expression Recognition via an Attention Refinement Network

Jiayi Liu, Qiufeng Wang*, Wei Liao, Jianghan Chen, Kaizhu Huang

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

Handwritten mathematical expression recognition (HMER), typically regarding as a sequence-to-sequence problem, has made great progress in recent years, where RNN based models have been widely adopted. Although Transformer based model has demonstrated success in many areas, its performance is not satisfied due to the issue of standard attention mechanism in HMER. Therefore, we propose to improve the performance via an attention refinement network in the Transformer framework for HMER. We firstly adopt a shift window attention (SWA) from Swin Transformer to capture spatial contexts of the whole image for HMER. Moreover, we propose a refined coverage attention (RCA) to overcome the issue of lack of converge in the standard attention mechanism, where we utilize a convolutional kernel with a gating function to obtain coverage features. With the proposed RCA, we refine coverage attentions to attenuate the repeating issue of focused areas in the long-sequence. In addition, we utilize a pyramid data augmentation method to generate mathematical expression images with multiple resolutions to enhance the model generalization. We evaluate the proposed attention refinement network on the HMER benchmark datasets of CROHME2014/2016/2019, and extensive experiments demonstrate its effectiveness.

Original languageEnglish
Title of host publicationNeural Information Processing - 30th International Conference, ICONIP 2023, Proceedings
EditorsBiao Luo, Long Cheng, Zheng-Guang Wu, Hongyi Li, Chaojie Li
PublisherSpringer Science and Business Media Deutschland GmbH
Pages543-555
Number of pages13
ISBN (Print)9789819981779
DOIs
Publication statusPublished - 2024
Event30th International Conference on Neural Information Processing, ICONIP 2023 - Changsha, China
Duration: 20 Nov 202323 Nov 2023

Publication series

NameCommunications in Computer and Information Science
Volume1967 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference30th International Conference on Neural Information Processing, ICONIP 2023
Country/TerritoryChina
CityChangsha
Period20/11/2323/11/23

Keywords

  • Handwritten mathematical expression recognition
  • Pyramid data augmentation
  • Refined coverage attention
  • Shift window attention

Fingerprint

Dive into the research topics of 'Improving Handwritten Mathematical Expression Recognition via an Attention Refinement Network'. Together they form a unique fingerprint.

Cite this