Scene text recognition via dual character counting-aware visual and semantic modeling network
文献类型:期刊论文
作者 | Xiao, Ke1; Zhu, Anna1; Iwana, Brian Kenji2; Liu, Cheng-Lin3,4 |
刊名 | SCIENCE CHINA-INFORMATION SCIENCES |
出版日期 | 2024-03-01 |
卷号 | 67期号:3页码:2 |
ISSN号 | 1674-733X |
DOI | 10.1007/s11432-023-3935-8 |
通讯作者 | Zhu, Anna(annazhu@whut.edu.cn) |
英文摘要 | ConclusionIn this work, we study character counting in STR from a new viewpoint, giving a principled framework showing that the counting information is involved in both visual decoding and semantic decoding. Based on the principled framework, we propose a novel scene text recognizer with a dual character counting-aware visual and semantic modeling network, where the counting information is fused in both vision and language branches. Experimental results demonstrate the effectiveness of our model. |
资助项目 | Open Project Program of the National Laboratory of Pattern Recognition (NLPR)[202200049] |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | SCIENCE PRESS |
WOS记录号 | WOS:001159964100002 |
资助机构 | Open Project Program of the National Laboratory of Pattern Recognition (NLPR) |
源URL | [http://ir.ia.ac.cn/handle/173211/55355] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Zhu, Anna |
作者单位 | 1.Wuhan Univ Technol, Sch Comp Sci & Artificial Intelligence, Wuhan 430070, Peoples R China 2.Kyushu Univ, Human Interface Lab, Fukuoka 8190395, Japan 3.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Xiao, Ke,Zhu, Anna,Iwana, Brian Kenji,et al. Scene text recognition via dual character counting-aware visual and semantic modeling network[J]. SCIENCE CHINA-INFORMATION SCIENCES,2024,67(3):2. |
APA | Xiao, Ke,Zhu, Anna,Iwana, Brian Kenji,&Liu, Cheng-Lin.(2024).Scene text recognition via dual character counting-aware visual and semantic modeling network.SCIENCE CHINA-INFORMATION SCIENCES,67(3),2. |
MLA | Xiao, Ke,et al."Scene text recognition via dual character counting-aware visual and semantic modeling network".SCIENCE CHINA-INFORMATION SCIENCES 67.3(2024):2. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
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。