Knowledge Commons of Institute of Automation,CAS
Cross-Modal Prototype Learning for Zero-Shot Handwritten Character Recognition | |
Ao, Xiang1,2![]() ![]() ![]() | |
发表期刊 | Pattern Recognition
![]() |
2022 | |
卷号 | 131页码:108859 |
摘要 | Traditional methods of handwritten character recognition rely on extensive labeled data. However, humans can generalize to unseen handwritten characters by watching a few printed examples in textbooks. To simulate this ability, we propose a cross-modal prototype learning method (CMPL) to realize zero-shot recognition. For each character class, a prototype is generated by mapping the printed character into a deep neural network feature space. For unseen character class, its prototype can be directly produced from a printed character sample, therefore, not requiring any handwritten samples to realize class-incremental learning. Specifically, CMPL considers different modalities simultaneously - online handwritten trajectories, offline handwritten images, and auxiliary printed character images. The joint learning of the above modalities is achieved through sharing printed prototypes between online and offline data. In zero-shot inference, we feed CMPL the printed samples to obtain corresponding class prototypes, and then the unseen handwritten character can be recognized by the nearest prototype. Our experimental results demonstrate that CMPL outperforms the state-of-the-art methods in both online and offline zero-shot handwritten Chinese character recognition. Moreover, we also show the cross-domain generalization of CMPL from two perspectives: cross-language and modern-to-ancient handwritten character recognition, focusing on the transferability between different languages and different styles (i.e., modern and historical handwritings). |
收录类别 | SCI |
语种 | 英语 |
WOS记录号 | WOS:000834134500013 |
七大方向——子方向分类 | 文字识别与文档分析 |
国重实验室规划方向分类 | 小样本高噪声数据学习 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56730 |
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 | Zhang, Xu-Yao |
作者单位 | 1.National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing 100190, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing 100049, China |
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 | Ao, Xiang,Zhang, Xu-Yao,Liu, Cheng-Lin. Cross-Modal Prototype Learning for Zero-Shot Handwritten Character Recognition[J]. Pattern Recognition,2022,131:108859. |
APA | Ao, Xiang,Zhang, Xu-Yao,&Liu, Cheng-Lin.(2022).Cross-Modal Prototype Learning for Zero-Shot Handwritten Character Recognition.Pattern Recognition,131,108859. |
MLA | Ao, Xiang,et al."Cross-Modal Prototype Learning for Zero-Shot Handwritten Character Recognition".Pattern Recognition 131(2022):108859. |
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 | ||
1-s2.0-S003132032200(3111KB) | 期刊论文 | 作者接受稿 | 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