Knowledge Commons of Institute of Automation,CAS
Sequence-to-Sequence Domain Adaptation Network for Robust Text Image Recognition | |
Zhang, Yaping1,2![]() ![]() ![]() | |
2019-06 | |
会议名称 | CVPR |
会议日期 | 2019.06.16-2019.06.20 |
会议地点 | Long Beach, CA |
摘要 | Domain adaptation has shown promising advances for alleviating domain shift problem. However, recent visual domain adaptation works usually focus on non-sequential object recognition with a global coarse alignment, which is inadequate to transfer effective knowledge for sequence-like text images with variable-length fine-grained character information. In this paper, we develop a Sequence-toSequence Domain Adaptation Network (SSDAN) for robust text image recognition, which could exploit unsupervised sequence data by an attention-based sequence encoderdecoder network. In the SSDAN, a gated attention similarity (GAS) unit is introduced to adaptively focus on aligning the distribution of the source and target sequence data in an attended character-level feature space rather than a global coarse alignment. Extensive text recognition experiments show the SSDAN could efficiently transfer sequence knowledge and validate the promising power of the proposed model towards real world applications in various recognition scenarios, including the natural scene text, handwritten text and even mathematical expression recognition. |
关键词 | Domain Adaptation Text Image Recognition |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/38562 |
专题 | 多模态人工智能系统全国重点实验室_智能交互 |
通讯作者 | Liu, Wenju |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.University of Electronic Science and Technology of China 4.Zhejiang University 5.Afanti AI Lab |
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 | Zhang, Yaping,Nie, Shuai,Liu, Wenju,et al. Sequence-to-Sequence Domain Adaptation Network for Robust Text Image Recognition[C],2019. |
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 | ||
seqda_cvpr2019_1786.(718KB) | 会议论文 | 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