DyGAT: Dynamic stroke classification of online handwritten documents and sketches

doi:10.1016/j.patcog.2023.109564

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	DyGAT: Dynamic stroke classification of online handwritten documents and sketches
	Yang, Yu-Ting 1,2; Zhang, Yan-Ming 1; Yun, Xiao-Long 1; Yin, Fei 1; Liu, Cheng-Lin 1
刊名	PATTERN RECOGNITION
	2023-09-01
卷号	141 页码:12
关键词	Stroke classification Sketch semantic segmentation Document layout analysis Diagram recognition Streaming recognition
ISSN号	0031-3203
DOI	10.1016/j.patcog.2023.109564
通讯作者	Zhang, Yan-Ming(ymzhang@nlpr.ia.ac.cn)
英文摘要	Online handwriting is widely used in human-machine interface, education, office automation, and so on. Stroke classification for online handwritten documents and sketches aims to divide strokes into several semantic categories and is a necessary step for document recognition and understanding. Previous methods are essentially static in that they have to wait for the user to finish the whole sketch before making prediction. However, in practice, the more user-friendly way is to make real-time prediction as the user is writing. In this paper, we introduce Dynamic Graph ATtention network (DyGAT) to solve the dynamic stroke classification problem. The core of our method is to formalize a document/sketch into a multifeature graph, in which nodes represent strokes, edges represent the relationships between strokes, and multiple nodes are applied to one stroke to control the information flow. The proposed method is general and is applicable to online handwritten data of many types. We conduct experiments on popular public datasets to perform sketch semantic segmentation, document layout analysis and diagram recognition, and experimental results show competitive performance. Particularly, the proposed method achieves stroke classification accuracies which are only slightly lower than those of static classification.(c) 2023 Elsevier Ltd. All rights reserved.
资助项目	Major Project for New Genera- tion of AI[2018AAA010 040 0] ; National Natural Science Foundation of China (NSFC)[61773376] ; National Natural Science Foundation of China (NSFC)[62276258]
WOS关键词	MODE DETECTION
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000987045600001
资助机构	Major Project for New Genera- tion of AI ; National Natural Science Foundation of China (NSFC)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53254]
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 Automation, 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	Yang, Yu-Ting,Zhang, Yan-Ming,Yun, Xiao-Long,et al. DyGAT: Dynamic stroke classification of online handwritten documents and sketches[J]. PATTERN RECOGNITION,2023,141:12.
APA	Yang, Yu-Ting,Zhang, Yan-Ming,Yun, Xiao-Long,Yin, Fei,&Liu, Cheng-Lin.(2023).DyGAT: Dynamic stroke classification of online handwritten documents and sketches.PATTERN RECOGNITION,141,12.
MLA	Yang, Yu-Ting,et al."DyGAT: Dynamic stroke classification of online handwritten documents and sketches".PATTERN RECOGNITION 141(2023):12.