Metraipolis › archive › dc_ffe488ea1ce6

MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understanding — arXiv:2608.10706

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.10706
License (as archived): CC0-1.0
Archived: 2026-10-19T06:30:24.412Z
SHA-256 of the archived text: 02151fda86d3d4150fdc27acd0e9772b45421f48bdf0b96edd466a528183dcbb
Stable URL of this page: https://metraipolis.com/documento/dc_ffe488ea1ce6

How to cite

MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understanding — arXiv:2608.10706 — arXiv (en), https://arxiv.org/abs/2608.10706 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ffe488ea1ce6 (Metraipolis archive dc_ffe488ea1ce6, sha256 02151fda86d3d4150fdc27acd0e9772b45421f48bdf0b96edd466a528183dcbb)

BibTeX

@misc{dcffe488ea1ce6,
  title = {MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understanding — arXiv:2608.10706},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10706},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ffe488ea1ce6; sha256 02151fda86d3d4150fdc27acd0e9772b45421f48bdf0b96edd466a528183dcbb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10706. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent vision-language models demonstrate impressive general visual understanding, yet their art interpretation remains shallow: they describe surface content but struggle with formal analysis, grounded historical interpretation, or affective characterization. We argue this is not only a model but also a dataset limitation. Existing art datasets are single perspective resources, where no dataset provides narrative, formal, emotional, and historical perspectives simultaneously for the same artworks. We introduce MMArt, a large-scale dataset of 74,234 WikiArt paintings, each annotated with four independently annotated perspectives plus a harmonized unified caption, produced by specialized vision-language models or human annotation and validated through complementary quality evaluations. Two complementarity analyses establish that perspectives encode genuinely distinct information. A generative analysis shows that formal analysis descriptions best preserve compositional style, and historical descriptions carry strong affective signal in reconstructed images. A discriminative retrieval analysis reveals task-asymmetry: narrative descriptions drive retrieval (R@1 = 44.0%), while formal descriptions, strongest for reconstruction, are nearly nondiscriminative at retrieval scale (R@1 = 7.8%). Leave-one-out analysis further confirms that historical descriptions are the least replaceable perspective across both tasks. Together, the two analyses establish that no single perspective suffices for all tasks, directly motivating MMArt multi-perspective design. The dataset, code, and additional information are available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.10706 — 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 2026-10-19T06:25:27.273Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).