method: sample-32023-03-21

Authors: Zhenrong Zhang, Lei Jiang, Youhui Guo, Jianshu Zhang, Jun Du

Affiliation: University of Science and Technology of China (USTC), iFLYTEK AI Research

Email: zzr666@mail.ustc.edu.cn

Description: 1. We use the GraphDoc[1] to perform bounding box classification, which utilizes text, layout, and visual information simultaneously.

[1] Zhenrong Zhang, Jiefeng Ma, Jun Du, Licheng Wang and Jianshu Zhang. Multimodal Pre-training Based on Graph Attention Network for Document Understanding. 2022, TMM.