Metraipolis › archive › dc_a87f3aaab1f8
Video Evidence Indexing: Learning Where to Look from Video Previews for Token-Budgeted Long-Video Question Answering — arXiv:2610.00757
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00757
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T19:11:37.752Z
- SHA-256 of the archived text
2bd0d0521f4c08cb47096d5ce9bba7143b1307bc0880e5ce06d68b723048c6aa- Stable URL of this page
https://metraipolis.com/documento/dc_a87f3aaab1f8
How to cite
Video Evidence Indexing: Learning Where to Look from Video Previews for Token-Budgeted Long-Video Question Answering — arXiv:2610.00757 — arXiv (en), https://arxiv.org/abs/2610.00757 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a87f3aaab1f8 (Metraipolis archive dc_a87f3aaab1f8, sha256 2bd0d0521f4c08cb47096d5ce9bba7143b1307bc0880e5ce06d68b723048c6aa)
BibTeX
@misc{dca87f3aaab1f8,
title = {Video Evidence Indexing: Learning Where to Look from Video Previews for Token-Budgeted Long-Video Question Answering — arXiv:2610.00757},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00757},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a87f3aaab1f8; sha256 2bd0d0521f4c08cb47096d5ce9bba7143b1307bc0880e5ce06d68b723048c6aa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00757. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-video question answering is limited by the high cost of visual tokens and by the fixed context width of current VLMs. A long-video question may require broad temporal coverage, but the answer is often supported by only a compact set of moments. To locate these moments efficiently, we propose token-budgeted Video Evidence Indexing (VEI): given a dense low-resolution Video Preview, the model constructs a compact high-resolution Evidence Set for final reasoning. We treat VEI as a policy that must jointly solve \textit{evidence localization}, which finds question-relevant moments, and \textit{budget planning}, which decides where to spend the limited high-resolution frame budget. We implement this idea with an inference pipeline: the Video Preview provides cheap global coverage, Video Evidence Indexing constructs the Evidence Set, and Answer Generation combines both inputs for final VQA. To address missing frame-level supervision, we adopt privileged self-distillation, where an answer-aware teacher guides the normal test-time policy on student-generated indexing traces. We explore previews at 1, 6, 12, and 24 visual tokens per frame, training a single policy that supports all four resolutions. Experiments show that Video Evidence Indexing improves accuracy under limited visual budgets, and self-distillation further improves both QA accuracy and temporal evidence localization.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.00757 — 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 2026-10-06T17:37:36.697Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).