Metraipolis › archive › dc_c24a8e331e65

Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding — arXiv:2609.11899

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11899
License (as archived)
CC0-1.0
Archived
2026-10-16T05:54:37.139Z
SHA-256 of the archived text
d4785beb07f49c7e58eccf7abb12ba0b240c3cd745258befd2602d238bd6de29
Stable URL of this page
https://metraipolis.com/documento/dc_c24a8e331e65

How to cite

Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding — arXiv:2609.11899 — arXiv (en), https://arxiv.org/abs/2609.11899 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c24a8e331e65 (Metraipolis archive dc_c24a8e331e65, sha256 d4785beb07f49c7e58eccf7abb12ba0b240c3cd745258befd2602d238bd6de29)
BibTeX
@misc{dcc24a8e331e65,
  title = {Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding — arXiv:2609.11899},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11899},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c24a8e331e65; sha256 d4785beb07f49c7e58eccf7abb12ba0b240c3cd745258befd2602d238bd6de29},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11899. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-video understanding on edge devices must reason over hours of content under tight compute and bandwidth budgets. Subsampling visual tokens loses temporal structure, while text-only video memories lose fine-grained visual attributes. We observe a visual-textual duality: language memories carry long-range temporal structure better than dense frames, while pixels remain decisive for attribute-level perception. Building on this insight, we propose Caption-once, Frames-onDemand (CFD), a budget-aware edge-cloud agentic framework. The edge runs a single offline captioning pass that builds a dual-track narrative index, an event-level story skeleton plus a clip-level micro-log, cached and reused across queries without re-captioning. At query time, a cloud-side MLLM reasons over the index in a story-first loop centered on a lightweight Visual-Need Router: a per-query gating module that triggers bounded keyframe retrieval only for perceptual questions (appearance, on-screen text, attribute disambiguation) and keeps temporal-structural questions in language space. The router turns visual access into a first-class, query-conditioned cost, capping per-query frame consumption regardless of video length. Experiments on long-video benchmarks demonstrate strong accuracy-efficiency trade-offs while substantially reducing online visual processing.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.HC).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.11899 — 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 2026-10-16T05:40:47.039Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).