cs.CVNov 3, 2026

EP-LVMQA: Evidence-Preserving Coarse-to-Fine Localization for Low-Quality Long Video Moment Question Answering

Authors: Guoning Chen, Zhexun Hu, Yifan Wei, Yixuan Weng, Bin Li, Yufei Zhao

Organizations: Nanyang Technological University, Singapore · ByteDance Inc. · State Key Laboratory of Complex and Critical Software Environment, School of Computer Science and Engineering, Beihang University · Westlake University · 

Abstract

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.

Figures & tables

Explore similar work

CardsList
  1. Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos

    Aug 26, 2026Baixuan Xu, Yinyui Xu, Tianshi Zheng +9Long-Video QALong-Video Understanding

  2. Evidence-Backed Video Question Answering

    Jul 13, 2026Shijie Wang, Honglu Zhou, Ziyang Wang +5Temporal Video GroundingVideo Question Answering