@inproceedings{hayashi-etal-2024-towards,
title = "Towards Artwork Explanation in Large-scale Vision Language Models",
author = "Hayashi, Kazuki and
Sakai, Yusuke and
Kamigaito, Hidetaka and
Hayashi, Katsuhiko and
Watanabe, Taro",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-short.65/",
doi = "10.18653/v1/2024.acl-short.65",
pages = "705--729",
abstract = "Large-scale Vision-Language Models (LVLMs) output text from images and instructions, demonstrating advanced capabilities in text generation and comprehension. However, it has not been clarified to what extent LVLMs understand the knowledge necessary for explaining images, the complex relationships between various pieces of knowledge, and how they integrate these understandings into their explanations. To address this issue, we propose a new task: the artwork explanation generation task, along with its evaluation dataset and metric for quantitatively assessing the understanding and utilization of knowledge about artworks. This task is apt for image description based on the premise that LVLMs are expected to have pre-existing knowledge of artworks, which are often subjects of wide recognition and documented information.It consists of two parts: generating explanations from both images and titles of artworks, and generating explanations using only images, thus evaluating the LVLMs' language-based and vision-based knowledge.Alongside, we release a training dataset for LVLMs to learn explanations that incorporate knowledge about artworks.Our findings indicate that LVLMs not only struggle with integrating language and visual information but also exhibit a more pronounced limitation in acquiring knowledge from images alone. The datasets ExpArt=Explain Artworks are available at https://huggingface.co/datasets/naist-nlp/ExpArt"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hayashi-etal-2024-towards">
<titleInfo>
<title>Towards Artwork Explanation in Large-scale Vision Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazuki</namePart>
<namePart type="family">Hayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhiko</namePart>
<namePart type="family">Hayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale Vision-Language Models (LVLMs) output text from images and instructions, demonstrating advanced capabilities in text generation and comprehension. However, it has not been clarified to what extent LVLMs understand the knowledge necessary for explaining images, the complex relationships between various pieces of knowledge, and how they integrate these understandings into their explanations. To address this issue, we propose a new task: the artwork explanation generation task, along with its evaluation dataset and metric for quantitatively assessing the understanding and utilization of knowledge about artworks. This task is apt for image description based on the premise that LVLMs are expected to have pre-existing knowledge of artworks, which are often subjects of wide recognition and documented information.It consists of two parts: generating explanations from both images and titles of artworks, and generating explanations using only images, thus evaluating the LVLMs’ language-based and vision-based knowledge.Alongside, we release a training dataset for LVLMs to learn explanations that incorporate knowledge about artworks.Our findings indicate that LVLMs not only struggle with integrating language and visual information but also exhibit a more pronounced limitation in acquiring knowledge from images alone. The datasets ExpArt=Explain Artworks are available at https://huggingface.co/datasets/naist-nlp/ExpArt</abstract>
<identifier type="citekey">hayashi-etal-2024-towards</identifier>
<identifier type="doi">10.18653/v1/2024.acl-short.65</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-short.65/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>705</start>
<end>729</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Artwork Explanation in Large-scale Vision Language Models
%A Hayashi, Kazuki
%A Sakai, Yusuke
%A Kamigaito, Hidetaka
%A Hayashi, Katsuhiko
%A Watanabe, Taro
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F hayashi-etal-2024-towards
%X Large-scale Vision-Language Models (LVLMs) output text from images and instructions, demonstrating advanced capabilities in text generation and comprehension. However, it has not been clarified to what extent LVLMs understand the knowledge necessary for explaining images, the complex relationships between various pieces of knowledge, and how they integrate these understandings into their explanations. To address this issue, we propose a new task: the artwork explanation generation task, along with its evaluation dataset and metric for quantitatively assessing the understanding and utilization of knowledge about artworks. This task is apt for image description based on the premise that LVLMs are expected to have pre-existing knowledge of artworks, which are often subjects of wide recognition and documented information.It consists of two parts: generating explanations from both images and titles of artworks, and generating explanations using only images, thus evaluating the LVLMs’ language-based and vision-based knowledge.Alongside, we release a training dataset for LVLMs to learn explanations that incorporate knowledge about artworks.Our findings indicate that LVLMs not only struggle with integrating language and visual information but also exhibit a more pronounced limitation in acquiring knowledge from images alone. The datasets ExpArt=Explain Artworks are available at https://huggingface.co/datasets/naist-nlp/ExpArt
%R 10.18653/v1/2024.acl-short.65
%U https://aclanthology.org/2024.luhme-short.65/
%U https://doi.org/10.18653/v1/2024.acl-short.65
%P 705-729
Markdown (Informal)
[Towards Artwork Explanation in Large-scale Vision Language Models](https://aclanthology.org/2024.luhme-short.65/) (Hayashi et al., ACL 2024)
ACL
- Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, and Taro Watanabe. 2024. Towards Artwork Explanation in Large-scale Vision Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 705–729, Bangkok, Thailand. Association for Computational Linguistics.