中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 三维可视计算
Cross-lingual font style transfer with full-domain convolutional attention

文献类型：期刊论文

作者Zhao, Hui-huang1,2; Ji, Tian-le2; Rosin, Paul L.3; Lai, Yu-Kun3; Meng, Wei-liang4,5; Wang, Yao-nan1
刊名PATTERN RECOGNITION
出版日期2024-11-01
卷号155页码:15
关键词Cross-lingual Full-domain convolutional attention Multi-layer perceptual discriminator Font style transfer
ISSN号0031-3203
DOI10.1016/j.patcog.2024.110709
通讯作者Zhao, Hui-huang(happyday.huihuang@gmail.com)
英文摘要In this paper, we propose a new cross -lingual font style transfer model, FCAGAN, which enables font style transfer between different languages by observing a small number of samples. Most previous work has been on style transfer of different fonts for single language content, but in our task we can learn the font style of one language and migrate it to another. We investigated the drawbacks of related studies and found that existing cross -lingual approaches cannot perfectly learn styles from other languages and maintain the integrity of their own content. Therefore, we designed a new full -domain convolutional attention (FCA) module in combination with other modules to better learn font styles, and a multi -layer perceptual discriminator to ensure character integrity. Experiments show that using this model provides more satisfying results than the current cross -lingual font style transfer methods. Code can be found at https://github.com/jtlxlf/FCAGAN.
资助项目National Natural Science Foundation of China[61772179] ; Hunan Provincial Natural Science Foundation of China[2024JJ5059] ; Hunan Provincial Natural Science Foundation of China[2023JJ50095] ; Hunan Provincial Natural Science Foundation of China[2022JJ50016] ; The 14th Five-Year PlanKey Disciplines and Application-oriented Special Disciplines of Hunan Province[[2022] 351] ; Science and Technology Plan Project of Hunan Province, China[2016TP1020]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001264442600001
出版者ELSEVIER SCI LTD
资助机构National Natural Science Foundation of China ; Hunan Provincial Natural Science Foundation of China ; The 14th Five-Year PlanKey Disciplines and Application-oriented Special Disciplines of Hunan Province ; Science and Technology Plan Project of Hunan Province, China
源URL[http://ir.ia.ac.cn/handle/173211/59202]  
专题模式识别国家重点实验室_三维可视计算
通讯作者Zhao, Hui-huang
作者单位1.Hengyang Normal Univ, Sch Comp Sci & Technol, Hengyang 421002, Peoples R China
2.Hunan Univ, Natl Engn Lab Robot Visual Percept & Control Techn, Changsha, Peoples R China
3.Cardiff Univ, Sch Comp Sci & Informat, Cardiff, Wales
4.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100098, Peoples R China
5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Zhao, Hui-huang,Ji, Tian-le,Rosin, Paul L.,et al. Cross-lingual font style transfer with full-domain convolutional attention[J]. PATTERN RECOGNITION,2024,155:15.
APA Zhao, Hui-huang,Ji, Tian-le,Rosin, Paul L.,Lai, Yu-Kun,Meng, Wei-liang,&Wang, Yao-nan.(2024).Cross-lingual font style transfer with full-domain convolutional attention.PATTERN RECOGNITION,155,15.
MLA Zhao, Hui-huang,et al."Cross-lingual font style transfer with full-domain convolutional attention".PATTERN RECOGNITION 155(2024):15.

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。