Zihao Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zihao Lin has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Fan Yang
School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China
1 shared publication - Jianmin Lin
CVTE Research
1 shared publication - Jinrong Li
CVTE Research
1 shared publication - Ming Yang
CVTE Research
1 shared publication - Shuangping Huang
South China University of Technology, Guangzhou, China
1 shared publication - Xu Yang
GRGBanking Equipment Co. Ltd. Guangzhou China
1 shared publication
Latest Publications
- Open Access
Spatial Attention and Syntax Rule Enhanced Tree Decoder for Offine Handwritten Mathematical Expression Recognition
Offline Handwritten Mathematical Expression Recognition (HMER) has been dramatically advanced recently by employing tree decoders as part of the encoder-decoder method. Despite the tree decoder-based methods regard the expressions as a tree and parse 2D spatial structure to the tree nodes sequence, the performance of existing works is still poor due to the inevitable tree nodes prediction errors. Besides, they lack syntax rules to regulate the output of expressions. In this paper, we propose a novel model called Spatial Attention and Syntax Rule Enhanced Tree Decoder (SS-TD), which is equipped with spatial attention mechanism to alleviate the prediction error of tree structure and use syntax masks (obtained from the transformation of syntax rules) to constrain the occurrence of ungrammatical mathematical expression. In this way, our model can effectively describe tree structure and increase the accuracy of output expression. Experiments show that SS-TD achieves better recognition performance than prior models on CROHME 14/16/19 datasets, demonstrating the effectiveness of our model.
Open AccessSpatial Attention and Syntax Rule Enhanced Tree Decoder for Offine Handwritten Mathematical Expression Recognition
Offline Handwritten Mathematical Expression Recognition (HMER) has been dramatically advanced recently by employing tree decoders as part of the encoder-decoder method. Despite the tree decoder-based methods regard the expressions as a tree and parse 2D spatial structure to the tree nodes sequence, the performance of existing works is still poor due to the inevitable tree nodes prediction errors. Besides, they lack syntax rules to regulate the output of expressions. In this paper, we propose a novel model called Spatial Attention and Syntax Rule Enhanced Tree Decoder (SS-TD), which is equipped with spatial attention mechanism to alleviate the prediction error of tree structure and use syntax masks (obtained from the transformation of syntax rules) to constrain the occurrence of ungrammatical mathematical expression. In this way, our model can effectively describe tree structure and increase the accuracy of output expression. Experiments show that SS-TD achieves better recognition performance than prior models on CROHME 14/16/19 datasets, demonstrating the effectiveness of our model.