Cross-Lingual Text Image Recognition via Multi-Hierarchy Cross-Modal Mimic | |
Chen, Zhuo1,2; Yin, Fei1,2; Yang, Qing1,2; Liu, Cheng-Lin1,2 | |
刊名 | IEEE TRANSACTIONS ON MULTIMEDIA |
2023 | |
卷号 | 25页码:4830-4841 |
关键词 | Cross-lingual text image recognition cross-modal mimic multihierarchy mimic |
ISSN号 | 1520-9210 |
DOI | 10.1109/TMM.2022.3183386 |
通讯作者 | Liu, Cheng-Lin(liucl@nlpr.ia.ac.cn) |
英文摘要 | Optical character recognition and machine translation are usually studied and applied separately. In this paper, we consider a new problem named cross-lingual text image recognition (CLTIR) that integrates these two tasks together. The core of this problem is to recognize source language texts shown in images and transcribe them to the target language in an end-to-end manner. Traditional cascaded systems perform text image recognition and text translation sequentially. This can lead to error accumulation and parameter redundancy problems. To overcome these problems, we propose a multihierarchy cross-modal mimic (MHCMM) framework for end-to-end CLTIR, which can be trained with a massive bilingual text corpus and a small number of bilingual annotated text images. In this framework, a plug-in machine translation model is used as a teacher to guide the CLTIR model for learning representations compatible with image and text modes. Via adversarial learning and attention mechanisms, the proposed mimic method can integrate both global and local information in the semantic space. Experiments on a newly collected dataset demonstrate the superiority of the proposed framework. Our method outperforms other pipelines while containing fewer parameters. Additionally, the MHCMM framework can utilize a large-scale bilingual corpus to further improve the performance efficiently. The visualization of attention scores indicates that the proposed model can read text images in a fashion similar to the machine translation model reading text tokens. |
资助项目 | National Key Research and Development Program[2020AAA0108003] ; National Natural Science Foundation of China[61733007] ; National Natural Science Foundation of China[61721004] |
WOS关键词 | SCENE TEXT |
WOS研究方向 | Computer Science ; Telecommunications |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:001097340300016 |
资助机构 | National Key Research and Development Program ; National Natural Science Foundation of China |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/55204] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Liu, Cheng-Lin |
作者单位 | 1.Chinese Acad Sci, Natl Lab Pattern Recognit NLPR, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Chen, Zhuo,Yin, Fei,Yang, Qing,et al. Cross-Lingual Text Image Recognition via Multi-Hierarchy Cross-Modal Mimic[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:4830-4841. |
APA | Chen, Zhuo,Yin, Fei,Yang, Qing,&Liu, Cheng-Lin.(2023).Cross-Lingual Text Image Recognition via Multi-Hierarchy Cross-Modal Mimic.IEEE TRANSACTIONS ON MULTIMEDIA,25,4830-4841. |
MLA | Chen, Zhuo,et al."Cross-Lingual Text Image Recognition via Multi-Hierarchy Cross-Modal Mimic".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):4830-4841. |
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