Metraipolis › archive › dc_86b656793fae
Learning visual representations for compositional analysis of artworks and photographs — arXiv:2608.06142
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.06142
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:37:42.234Z
- SHA-256 of the archived text
ffb5de984cc2699d57309a181fbf1d99539459c4be3aa831c2b60f32c03a49ed- Stable URL of this page
https://metraipolis.com/documento/dc_86b656793fae
How to cite
Learning visual representations for compositional analysis of artworks and photographs — arXiv:2608.06142 — arXiv (en), https://arxiv.org/abs/2608.06142 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_86b656793fae (Metraipolis archive dc_86b656793fae, sha256 ffb5de984cc2699d57309a181fbf1d99539459c4be3aa831c2b60f32c03a49ed)
BibTeX
@misc{dc86b656793fae,
title = {Learning visual representations for compositional analysis of artworks and photographs — arXiv:2608.06142},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.06142},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_86b656793fae; sha256 ffb5de984cc2699d57309a181fbf1d99539459c4be3aa831c2b60f32c03a49ed},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06142. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Composition, the deliberate arrangement of visual elements, is central to how meaning, emotion, and aesthetic quality are conveyed in artwork, yet it remains among the least formalized dimensions of visual understanding. Prior work highlights a persistent gap in learning meaningful compositional representations, attributing it to semantic bias and suggesting that human-inspired approaches may be key. We compare two parallel paradigms for composition analysis: a human-inspired method grounded in perceptual grouping, and fine-tuned foundation models enabled by recent large-scale compositional datasets. The human-inspired approach uses object-centric models for region-level decomposition and a graph attention network to capture spatial relationships between elements. Both paradigms are evaluated on composition score/category prediction, compositional image retrieval, and visual saliency detection. With frozen encoders, the human-inspired method achieves competitive performance while remaining interpretable. When sufficient data enables fine-tuning, large self-supervised models outperform significantly, but at the cost of interpretability and cross-domain generalization. Code and pre-trained models are available on GitHub. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.06142 — 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 2026-10-31T10:23:31.055Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).