Transformer-based stroke relation encoding for online handwriting and sketches
文献类型:期刊论文
作者 | Liu, Jing-Yu1,2; Zhang, Yan-Ming1; Yin, Fei1; Liu, Cheng-Lin1,2 |
刊名 | PATTERN RECOGNITION |
出版日期 | 2024-04-01 |
卷号 | 148页码:13 |
ISSN号 | 0031-3203 |
关键词 | Online stroke classification Handwritten document analysis Diagram recognition Sketch semantic segmentation Position encoding in transformer |
DOI | 10.1016/j.patcog.2023.110131 |
通讯作者 | Zhang, Yan-Ming(ymzhang@nlpr.ia.ac.cn) |
英文摘要 | Stroke classification for online handwriting and sketches, aimed at grouping strokes into different semantic categories, has drawn considerable attention due to its wide applications. This task is challenging since individual strokes look similar and are easily confused with each other. The key is to consider both the individual strokes and the contextual information jointly for making prediction. Previous methods are insufficient in modeling and exploiting complex contextual information of strokes. To overcome this limitation, we propose a Transformer-based model for Online Handwriting and Sketches (T-OHS), with novel relation encoding schemes to take advantage of temporal and spatial information in stroke sequence. Particularly, we introduce a coarse-to-fine hierarchical encoding approach based on the polar coordinate system for precisely modeling spatial relations between strokes. Experiments on three types of handwriting data, including online handwritten documents, diagrams, and sketches, demonstrate that our method is universal and provides state-of-the-art performance. |
WOS关键词 | MODE DETECTION ; CLASSIFICATION ; SEGMENTATION ; DOCUMENTS |
资助项目 | Major Project for New Generation AI[2018AAA0100400] ; National Natural Science Foundation of China (NSFC)[62276258] |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | ELSEVIER SCI LTD |
WOS记录号 | WOS:001128645600001 |
资助机构 | Major Project for New Generation AI ; National Natural Science Foundation of China (NSFC) |
源URL | [http://ir.ia.ac.cn/handle/173211/54979] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Zhang, Yan-Ming |
作者单位 | 1.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Liu, Jing-Yu,Zhang, Yan-Ming,Yin, Fei,et al. Transformer-based stroke relation encoding for online handwriting and sketches[J]. PATTERN RECOGNITION,2024,148:13. |
APA | Liu, Jing-Yu,Zhang, Yan-Ming,Yin, Fei,&Liu, Cheng-Lin.(2024).Transformer-based stroke relation encoding for online handwriting and sketches.PATTERN RECOGNITION,148,13. |
MLA | Liu, Jing-Yu,et al."Transformer-based stroke relation encoding for online handwriting and sketches".PATTERN RECOGNITION 148(2024):13. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
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。