Metraipolis › archive › dc_d0505058b321

Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG — arXiv:2608.23011

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.23011
License (as archived)
CC0-1.0
Archived
2026-10-18T07:45:09.118Z
SHA-256 of the archived text
ebc43352fa5acfd898fbe38ff0d7758368e8e595d07ca3f7f2e53a4bc58d92a5
Stable URL of this page
https://metraipolis.com/documento/dc_d0505058b321

How to cite

Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG — arXiv:2608.23011 — arXiv (en), https://arxiv.org/abs/2608.23011 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d0505058b321 (Metraipolis archive dc_d0505058b321, sha256 ebc43352fa5acfd898fbe38ff0d7758368e8e595d07ca3f7f2e53a4bc58d92a5)
BibTeX
@misc{dcd0505058b321,
  title = {Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG — arXiv:2608.23011},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23011},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d0505058b321; sha256 ebc43352fa5acfd898fbe38ff0d7758368e8e595d07ca3f7f2e53a4bc58d92a5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23011. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph-based retrieval-augmented generation (RAG) provides a scalable paradigm for long-video understanding, but existing systems typically inherit a fixed temporal granularity from video segmentation when constructing their retrieval index. We argue that this design unnecessarily couples indexing granularity with evidence granularity: coarse representations can often suffice for locating relevant temporal regions, while fine-grained evidence remains important for downstream reasoning. We propose \textbf{Density-Aware Graph Construction (DAGC)}, a training-free approach that decouples a query-independent coarse retrieval index from the original fine-grained evidence space. DAGC constructs a compact, density-adaptive graph index by merging visually redundant neighboring chunks, while preserving mappings to the original temporal units. Retrieved coarse regions are subsequently expanded back to the original chunk granularity for fine-grained evidence refinement and answer generation. Experiments on MLVU, VideoMME, and LongVideoBench show that DAGC retains only about 40--50\% of the original graph nodes and achieves $1.3$--$1.7\times$ end-to-end wall-clock acceleration while preserving approximately 99\% of the original QA performance. The gains transfer across different LVLM backbones and video RAG pipelines, suggesting that long-video RAG need not maintain the same temporal granularity for indexing and evidence reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.23011 — 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 2026-10-18T07:37:52.912Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).