Metraipolis › archive › dc_e656de226728
EP-LVMQA: Evidence-Preserving Coarse-to-Fine Localization for Low-Quality Long Video Moment Question Answering — arXiv:2611.04913
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04913
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T19:04:46.456Z
- SHA-256 of the archived text
10d73a0a318cffc2dca6cee86b8b909a3e84061dc6cff5470ba511e88bce008d- Stable URL of this page
https://metraipolis.com/documento/dc_e656de226728
How to cite
EP-LVMQA: Evidence-Preserving Coarse-to-Fine Localization for Low-Quality Long Video Moment Question Answering — arXiv:2611.04913 — arXiv (en), https://arxiv.org/abs/2611.04913 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e656de226728 (Metraipolis archive dc_e656de226728, sha256 10d73a0a318cffc2dca6cee86b8b909a3e84061dc6cff5470ba511e88bce008d)
BibTeX
@misc{dce656de226728,
title = {EP-LVMQA: Evidence-Preserving Coarse-to-Fine Localization for Low-Quality Long Video Moment Question Answering — arXiv:2611.04913},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04913},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e656de226728; sha256 10d73a0a318cffc2dca6cee86b8b909a3e84061dc6cff5470ba511e88bce008d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04913. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long instructional videos are increasingly used in medical education, industrial training, and procedural knowledge transfer, yet their evidence is often incomplete or unreliable: subtitles may be missing, ASR noisy, OCR sparse, and decisive actions briefly shown without narration. Existing VideoQA systems typically return labels or free-form text, making answer support difficult to inspect. We study Long Video Moment Question Answering (LVMQA), where a system returns timestamped answer-supporting evidence. We propose EP-LVMQA, an evidence-preserving coarse-to-fine framework comprising an Uncertainty-Aware Multimodal Evidence Timeline, a Coarse Evidence Planner, and an Evidence-Conditioned Fine Localizer. An evidence card transfers planner scores, matched cues, source-confidence proxies, modality-specific evidence, neighboring context, and a temporal prior between the latter two modules. On MedVidQA, EP-LVMQA achieves 26.1 [email protected] and 31.8 mIoU, improving the strongest non-ours results by 6.3 and 5.1 points. It raises Suff.@2 and Ver.@2 to 25.4 and 22.6, gains of 9.5 and 8.8 points. Under matched low-quality perturbations, average relative degradation is reduced from the strongest non-ours value of 14.6% to 11.1%. On Ego4D-NLQ and QVHighlights, EP-LVMQA remains broadly comparable to established task-specific localization methods. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.04913 — 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 2026-11-04T18:39:37.545Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).