ArtCap: A Dataset for Image Captioning of Fine Art Paintings
文献类型:期刊论文
作者 | Lu, Yue3,4![]() ![]() ![]() ![]() |
刊名 | IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
![]() |
出版日期 | 2022-11-28 |
页码 | 12 |
关键词 | Dataset construction image captioning painting captioning |
ISSN号 | 2329-924X |
DOI | 10.1109/TCSS.2022.3223539 |
通讯作者 | Wang, Fei-Yue(feiyue.wang@ia.ac.cn) |
英文摘要 | The image captioning of fine art paintings aims at generating content descriptions for the paintings. Due to the complexity of modeling both image and language, this task usually needs sufficient training data. However, different from photographic image captioning, there are few satisfactory datasets for painting captioning. In this article, we introduce a painting captioning dataset (named the ArtCap dataset), which contains 3606 paintings and five descriptions for each painting. We present the carefully designed construction pipeline of our dataset and further evaluate our dataset from two aspects of annotation quality and application effectiveness, respectively. For the annotation quality, we compare the global characteristics, annotation content, and annotation consistency of our dataset with other painting descriptions datasets. For application effectiveness, we employ our dataset and other painting descriptions datasets to train image captioning models and analyze the captioning performances. The results demonstrate the promising annotation quality and application effectiveness of our dataset. |
资助项目 | Sky work Intelligence Culture & Technology Ltd. |
WOS研究方向 | Computer Science |
语种 | 英语 |
WOS记录号 | WOS:000912785400001 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
资助机构 | Sky work Intelligence Culture & Technology Ltd. |
源URL | [http://ir.ia.ac.cn/handle/173211/51069] ![]() |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
通讯作者 | Wang, Fei-Yue |
作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Labo ratory Management & Control Complex, Beijing 100190, Peoples R China 2.Natl Museum China, Inst Sci & Art, Beijing 100006, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Laboratoryfor Management & Control Compl, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Lu, Yue,Guo, Chao,Dai, Xingyuan,et al. ArtCap: A Dataset for Image Captioning of Fine Art Paintings[J]. IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,2022:12. |
APA | Lu, Yue,Guo, Chao,Dai, Xingyuan,&Wang, Fei-Yue.(2022).ArtCap: A Dataset for Image Captioning of Fine Art Paintings.IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,12. |
MLA | Lu, Yue,et al."ArtCap: A Dataset for Image Captioning of Fine Art Paintings".IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS (2022):12. |
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。