.png){kind=icon}
返回
SATD: syntax-aware handwritten mathematical expression recognition based on tree-structured transformer decoder
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-024-03372-9.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The complex two-dimensional structure poses huge challenges for handwritten mathematical expression recognition (HMER). Many researchers process the LaTeX sequence into a tree structure and then design tree decoders based on RNN to address this issue. However, RNNs have problems with long-term dependency due to their structural characteristics. Although Transformers solve the long-term dependency problem, tree decoders based on Transformers are rarely used for HMER because the attention coverage is significantly insufficient when the distance between parent and child nodes is large in tree structures. In this paper, we propose a novel offline HMER model SATD incorporating a tree decoder based on Transformer to learn the implicit structural relationships in LaTeX strings. Moreover, to address the issue of distant parent-child nodes, we introduce a multi-scale attention aggregation module to refine attention weights using contextual information with different receptive fields. Experiments on CROHME2014/2016/2019 and HME100K datasets demonstrate performance improvements, achieving accuracy rates of 63.45%/60.42%/61.05% on the CROHME 2014/2016/2019 test sets. The source code https://github.com/EnderXiao/SATD/ of this work will be publicly available.
Keyword:
Offline handwritten mathematical expression recognition
Transformer
Coverage attention
Tree decoder
Attention
期刊
IF:
2.9
论文数:
4.6K
被引数:
6.5K
机构
引用论文
Sodium channel kinetic changes that produce Brugada syndrome or progressive cardiac conduction system disease产生Brugada综合征或进行性心脏传导系统疾病的钠通道动力学变化
.png){kind=icon}
PREAI
分享收藏分享收藏分享收藏
Comparative effect of phenobarbital and 3-methyl-cholanthrene on azodye metabolism in rat liver I. In vitro studies on detoxication and activation processes苯巴比妥和3-甲基胆蒽对偶氮染料代谢的比较效应。I. 关于解毒和活化过程的体外研究
PREAI
分享收藏Metal-organic chemical vapor deposition of indium selenide films using a single-source precursor使用单源前体对硒化铟薄膜进行金属有机化学气相沉积
PREAI
分享收藏
查看更多内容