Metraipolis › archive › dc_da8bad06cf8e

Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching — arXiv:2608.28695

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28695
License (as archived)
CC0-1.0
Archived
2026-10-17T09:44:20.668Z
SHA-256 of the archived text
d96bbc72fe8aed265e3240e2cf0508f76294bf6b942a6d2b49ac03cac32e6614
Stable URL of this page
https://metraipolis.com/documento/dc_da8bad06cf8e

How to cite

Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching — arXiv:2608.28695 — arXiv (en), https://arxiv.org/abs/2608.28695 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da8bad06cf8e (Metraipolis archive dc_da8bad06cf8e, sha256 d96bbc72fe8aed265e3240e2cf0508f76294bf6b942a6d2b49ac03cac32e6614)
BibTeX
@misc{dcda8bad06cf8e,
  title = {Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching — arXiv:2608.28695},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28695},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da8bad06cf8e; sha256 d96bbc72fe8aed265e3240e2cf0508f76294bf6b942a6d2b49ac03cac32e6614},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28695. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image retrieval has traditionally been formulated as a point-wise matching problem, where each candidate image is scored in isolation. However, this atomic paradigm fails to capture the complexity of human search intent within personal photo collections, where users often seek compact visual stories bound by structural relations rather than isolated snapshots. To address this limitation, we introduce **Image Bundle Composition (IBC)**, a novel paradigm that shifts the objective from ranking individual images to dynamically composing cohesive image bundles from a massive, unstructured photo pool. Since target bundles are not predefined, IBC presents a severe combinatorial explosion challenge and demands modeling non-decomposable joint relevance. To establish this paradigm, we construct **IBCBench**, the first IBC benchmark dataset containing 109,467 images and 667 verified queries, built via a semi-automated verification pipeline. Furthermore, we propose **BundleWeaver**, an agentic framework that reformulates IBC as query-conditioned incremental hyperedge discovery. By employing a Large Language Model to adaptively search for missing relational roles and utilizing a Vision-Language Model for whole-bundle verification, BundleWeaver effectively navigates the combinatorial space. Extensive experiments demonstrate that while state-of-the-art embedding models and static decompose-and-rerank paradigms suffer from relational blindness, BundleWeaver achieves substantial performance gains, highlighting the necessity of shifting from atomic scoring to dynamic relational composition. Our dataset and code are available.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.IR).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.28695 — 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 2026-10-17T09:12:53.490Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).