Metraipolis › archive › dc_cbbd11d20bcc
Concord: A Video Relational Algebra for Cross-Modal Query Optimization — arXiv:2609.05756
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05756
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:31:33.492Z
- SHA-256 of the archived text
96ed99ddc51a44c645fd38631ca3c8e6c8b510cca648a7cb90a244a7f7e75fab- Stable URL of this page
https://metraipolis.com/documento/dc_cbbd11d20bcc
How to cite
Concord: A Video Relational Algebra for Cross-Modal Query Optimization — arXiv:2609.05756 — arXiv (en), https://arxiv.org/abs/2609.05756 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbbd11d20bcc (Metraipolis archive dc_cbbd11d20bcc, sha256 96ed99ddc51a44c645fd38631ca3c8e6c8b510cca648a7cb90a244a7f7e75fab)
BibTeX
@misc{dccbbd11d20bcc,
title = {Concord: A Video Relational Algebra for Cross-Modal Query Optimization — arXiv:2609.05756},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05756},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbbd11d20bcc; sha256 96ed99ddc51a44c645fd38631ca3c8e6c8b510cca648a7cb90a244a7f7e75fab},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05756. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Semantic video queries let users embed natural language prompts and use multimodal large language models (MLLMs) to interpret the video. Such queries are increasingly popular for querying video data. However, their expressiveness comes at a steep cost: an MLLM may process hours of media to return only seconds of relevant output, making naive execution slow, expensive, and inaccurate. We propose Concord, a system for expressing and optimizing semantic video queries. We makes three contributions. First, we introduce Video Relational Algebra (VRA), a nested algebra over videos, transcripts, frames, and object tracks that captures common semantic video operations. Second, we derive a set of approximate optimizations that rewrite VRA queries to reduce MLLM usage while improving result quality. For narrated video, Concord either processes transcripts instead of video or uses them to identify video clips for MLLM processing. For cross-camera queries without narration, detection and tracking replace a whole-video MLLM join with a track-level relational join. Third, we evaluate Concord on real-world videos. Across 4.59 hours of soccer broadcasts and 3.92 hours of lectures, transcript-to-video queries send only 5.32% and 2.47% of source-video duration to the MLLM and reduce MLLM cost by up to 87%. In two five-second highway clips with 18 manually adjudicated cross-camera vehicles, a Detect-Track-Join query improves F1 from .364 to .813 while making no MLLM calls. See our project at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.DB). Categorie arXiv: Databases (cs.DB) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.05756 — 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 2026-10-16T15:12:35.373Z dalla pagina https://arxiv.org/catchup/cs.DB/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).