Metraipolis › archive › dc_d8c673d35567
Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval — arXiv:2609.10008
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10008
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:59:55.850Z
- SHA-256 of the archived text
43ab51d788c2e48d56f13b284cd5ec14fe54b5872cedb220166159ec0d373600- Stable URL of this page
https://metraipolis.com/documento/dc_d8c673d35567
How to cite
Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval — arXiv:2609.10008 — arXiv (en), https://arxiv.org/abs/2609.10008 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8c673d35567 (Metraipolis archive dc_d8c673d35567, sha256 43ab51d788c2e48d56f13b284cd5ec14fe54b5872cedb220166159ec0d373600)
BibTeX
@misc{dcd8c673d35567,
title = {Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval — arXiv:2609.10008},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10008},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8c673d35567; sha256 43ab51d788c2e48d56f13b284cd5ec14fe54b5872cedb220166159ec0d373600},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10008. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Composed video retrieval (CoVR) searches a gallery for the target video that realizes a natural-language modification of a source clip. However, at gallery scale, this creates a fundamental tension: compact embeddings enable efficient, reusable search but can miss the transient actions, state changes, and subtle constraints that demand fine-grained video reasoning, whereas applying large multimodal models uniformly sacrifices scalability. To address these limitations, we propose that frozen foundation models should instead occupy complementary roles, with inference depth adapted to query difficulty. Based on this premise, we introduce \methodname{}, a framework for training-free \methodexpansion{}. Specifically, a composed-query embedding first searches reusable video-only gallery representations; uncertain queries undergo bounded reranking and candidate expansion; ambiguous edits trigger target-description generation; and only close leading candidates reach multimodal verification. To support these roles, frame selection, spatial resolution, and time cues are adapted to each stage. Across complete target-gallery evaluations, our method reaches state-of-the-art performance among training-free approaches, with 89.55 and 93.43 R@1 on Dense-WebVid-CoVR and CoVR-R, respectively (with more than +35\% and +25\% absolute margins to the closest counterpart). These results show that adaptively orchestrating foundation-model capabilities can combine scalable retrieval with fine-grained reasoning without task-specific training. The source code and all relevant guidelines are available on this https URL .
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.10008 — 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 2026-10-16T10:02:34.348Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).