Knowledge Commons of Institute of Automation,CAS
Image Captioning on Fine Art Paintings via Virtual Paintings | |
Lu Yue1,2; Guo Chao1,2; Dai Xingyuan1,2; Wang Fei-yue1 | |
2021 | |
会议名称 | IEEE International Conference on Digital Twins and Parallel Intelligence |
会议日期 | 2021-07 |
会议地点 | online |
摘要 | Machine learning in fine art paintings is attracting increasing attention recently. Image captioning of paintings is of great importance for painting analysis, but it is rarely studied. The paintings have abstract expressions and lack annotated datasets, leading to the data-hungry problem in painting captioning. Thus, painting captioning has more significant challenges than photographic image captioning. This paper makes a novel attempt at generating content descriptions of paintings. We generate virtual paintings using the style transfer technique to deal with the data-hungry problem, then train the painting captioning model via a two-step manner. We evaluate our method on an annotated small-scale painting captioning dataset and demonstrate our improvements. |
关键词 | 图像标注 绘画 风格迁移 平行艺术 |
收录类别 | EI |
语种 | 英语 |
WOS研究方向 | image captioning ; fine art paintings ; style transfer ; parallel art |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48732 |
专题 | 多模态人工智能系统全国重点实验室_平行智能技术与系统团队 |
通讯作者 | Wang Fei-yue |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Lu Yue,Guo Chao,Dai Xingyuan,et al. Image Captioning on Fine Art Paintings via Virtual Paintings[C],2021. |
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 | ||
Lu et al_2021_Image (892KB) | 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