Knowledge Commons of Institute of Automation,CAS
Contextual Stroke Classification in Online Handwritten Documents with Graph Attention Networks | |
Jun-Yu Ye1,2![]() ![]() ![]() ![]() | |
2019-09 | |
会议名称 | 2019 International Conference on Document Analysis and Recognition |
会议日期 | 2019-9 |
会议地点 | 澳大利亚,悉尼 |
摘要 | Classifying strokes into different categories is an essential preprocessing step in the automatic document understanding process. To tackle this task, it is crucial to integrate different types of contextual information. Previous methods which are based on conditional random fields or recurrent neural networks have some limitations in model capacity or computational cost. In this paper, we propose a novel framework based on graph attention networks to solve this problem, which casts the stroke classification problem into the node classification problem in a document graph. In the graph, each node represents a stroke and the edges are built from temporal and spatial interactions between strokes. Combined graph convolution with attention mechanisms to dynamically aggregate features from the neighborhood, our model is very flexible to control the message passing routine between different nodes and therefore has strong capability learning contextaware features. We perform comparison experiments on the IAMonDo dataset and experimental results demonstrate the superiority of our approach. |
语种 | 英语 |
七大方向——子方向分类 | 文字识别与文档分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/43289 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
通讯作者 | Cheng-Lin Liu |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation of Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Jun-Yu Ye,Yan-Ming Zhang,Qing Yang,et al. Contextual Stroke Classification in Online Handwritten Documents with Graph Attention Networks[C],2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
ICDAR2019-JunyuYe.pd(353KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论