Metraipolis › archive › dc_e297699bcfd1

ExpArt-KG: Artwork Image Description Generation through Iterative Exploration of Knowledge Graphs — arXiv:2609.00629

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00629
License (as archived)
CC0-1.0
Archived
2026-10-17T06:41:18.447Z
SHA-256 of the archived text
8cfcc6146239f1e9ece821aac3bbdd5d9da5261a324f7da3395cefd920938fe3
Stable URL of this page
https://metraipolis.com/documento/dc_e297699bcfd1

How to cite

ExpArt-KG: Artwork Image Description Generation through Iterative Exploration of Knowledge Graphs — arXiv:2609.00629 — arXiv (en), https://arxiv.org/abs/2609.00629 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e297699bcfd1 (Metraipolis archive dc_e297699bcfd1, sha256 8cfcc6146239f1e9ece821aac3bbdd5d9da5261a324f7da3395cefd920938fe3)
BibTeX
@misc{dce297699bcfd1,
  title = {ExpArt-KG: Artwork Image Description Generation through Iterative Exploration of Knowledge Graphs — arXiv:2609.00629},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00629},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e297699bcfd1; sha256 8cfcc6146239f1e9ece821aac3bbdd5d9da5261a324f7da3395cefd920938fe3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00629. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Vision-Language Models (LVLMs) achieve strong performance on image-grounded text generation and visual question answering. However, it remains difficult for them to comprehensively and accurately describe the factual relations among the entities and concepts associated with the objects depicted in an image. In this work, we propose a framework that efficiently exploits factual information from a knowledge graph via retrieval-augmented generation (RAG), with the goal of enabling LVLMs to generate detailed and accurate image explanations. Specifically, our method alternates between answer generation and knowledge-graph retrieval, and controls the search using a correctness judgment, thereby acquiring the necessary and sufficient factual information efficiently. We also construct a knowledge graph for the artwork domain (ExpArt-KG), in which the correspondence between images and entities is unambiguous. Applying the proposed method to this knowledge graph, we show experimentally that it improves the level of detail of artwork explanations and reduces the retrieval cost of external knowledge while maintaining generation quality comparable to that of iterating a fixed number of times.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.00629 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:33:38.819Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).