Artwork Explanation in Large-scale Vision Language Models

arXiv:2403.00068v1 Announce Type: new
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 …

artwork arxiv cs.cv language language models scale type vision