Handwritten Mathematical Expression Recognition via Paired Adversarial Learning | |
Jin-Wen Wu1,3; Fei Yin3; Yan-Ming Zhang3; Xu-Yao Zhang1,3; Cheng-Lin Liu1,2,3 | |
刊名 | International Journal of Computer Vision |
2020 | |
卷号 | 128期号:128页码:2386-2401 |
关键词 | Handwritten ME recognition Paired adversarial learning Semantic-invariant features Convolutional decoder Coverage of decoding |
ISSN号 | 0920-5691 |
DOI | 10.1007/s11263-020-01291-5 |
通讯作者 | Wu, Jin-Wen(jinwen.wu@nlpr.ia.ac.cn) |
英文摘要 | Recognition of handwritten mathematical expressions (MEs) is an important problem that has wide applications in practice. HandwrittenME recognition is challenging due to the variety of writing styles andMEformats. As a result, recognizers trained by optimizing the traditional supervision loss do not perform satisfactorily. To improve the robustness of the recognizer with respect to writing styles, in this work, we propose a novel paired adversarial learning method to learn semantic-invariant features. Specifically, our proposed model, named PAL-v2, consists of an attention-based recognizer and a discriminator. During training, handwritten MEs and their printed templates are fed into PAL-v2 simultaneously. The attention-based recognizer is trained to learn semantic-invariant features with the guide of the discriminator. Moreover, we adopt a convolutional decoder to alleviate the vanishing and exploding gradient problems of RNN-based decoder, and further, improve the coverage of decoding with a novel attention method. We conducted extensive experiments on the CROHME dataset to demonstrate the effectiveness of each part of the method and achieved state-of-the-art performance. |
URL标识 | 查看原文 |
WOS关键词 | RETRIEVAL |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | SPRINGER |
WOS记录号 | WOS:000572233600003 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/40628] |
专题 | 自动化研究所_模式识别国家重点实验室_模式分析与学习团队 |
通讯作者 | Jin-Wen Wu |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, People’s Republic of China 2.CAS Center for Excellence of Brain Science and Intelligence Technology, Beijing 100190, People’s Republic of China 3.National Laboratory of Pattern Recognition, Institute of Automation of Chinese Academy of Sciences, Beijing 100190, People’s Republic of China |
推荐引用方式 GB/T 7714 | Jin-Wen Wu,Fei Yin,Yan-Ming Zhang,et al. Handwritten Mathematical Expression Recognition via Paired Adversarial Learning[J]. International Journal of Computer Vision,2020,128(128):2386-2401. |
APA | Jin-Wen Wu,Fei Yin,Yan-Ming Zhang,Xu-Yao Zhang,&Cheng-Lin Liu.(2020).Handwritten Mathematical Expression Recognition via Paired Adversarial Learning.International Journal of Computer Vision,128(128),2386-2401. |
MLA | Jin-Wen Wu,et al."Handwritten Mathematical Expression Recognition via Paired Adversarial Learning".International Journal of Computer Vision 128.128(2020):2386-2401. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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