跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2604.17422 · v3

Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding

首次提交 2026-04-19 21:04
版本更新 2026-11-13 11:27
雷达观测 2026-11-17 04:57
arXiv ↗PDF ↗

摘要

Long video understanding remains a formidable challenge for Multimodal Large Language Models (MLLMs) due to the prohibitive cost of processing dense frame sequences. Prevailing keyframe-selection methods rely on either a single visual-centric metric (e.g., CLIP similarity) or a static fusion of heuristic scores. This "one-size-fits-all" paradigm frequently fails: visual-only metrics are ineffective for plot-driven narrative queries, while indiscriminately adding textual scores introduces severe "modal noise" for purely visual tasks. To break this bottleneck, we propose Q-Gate, a plug-and-play, training-free framework that treats keyframe selection as a dynamic modality routing problem. We decouple retrieval into three lightweight expert streams: Visual Grounding for local details, Global Matching for scene semantics, and Contextual Alignment for subtitle-driven narratives. Crucially, Q-Gate introduces a Query-Modulated Gating Mechanism that uses the in-context reasoning of an LLM to assess query intent and dynamically allocate weights across the experts, activating necessary modalities while "muting" irrelevant ones to maximize the signal-to-noise ratio. Extensive experiments on LongVideoBench and Video-MME across multiple MLLM backbones show that Q-Gate outperforms representative keyframe-selection baselines in most settings, with particularly strong gains on long and medium videos, providing a robust and interpretable solution for scalable video reasoning. Code is available at https://github.com/shaoguangwang/Q_Gate

作者备注:10 pages, 5 figures. The 34th ACM International Conference on Multimedia (MM '26)

期刊信息:Proceedings of the 34th ACM International Conference on Multimedia (MM '26), pp. 10508-10517, 2026

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v3,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v3 · 2026-11-13 11:27 · 最新观测版本

Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding

Long video understanding remains a formidable challenge for Multimodal Large Language Models (MLLMs) due to the prohibitive cost of processing dense frame sequences. Prevailing keyframe-selection methods rely on either a single visual-centric metric (e.g., CLIP similarity) or a static fusion of heuristic scores. This "one-size-fits-all" paradigm frequently fails: visual-only metrics are ineffective for plot-driven narrative queries, while indiscriminately adding textual scores introduces severe "modal noise" for purely visual tasks. To break this bottleneck, we propose Q-Gate, a plug-and-play, training-free framework that treats keyframe selection as a dynamic modality routing problem. We decouple retrieval into three lightweight expert streams: Visual Grounding for local details, Global Matching for scene semantics, and Contextual Alignment for subtitle-driven narratives. Crucially, Q-Gate introduces a Query-Modulated Gating Mechanism that uses the in-context reasoning of an LLM to assess query intent and dynamically allocate weights across the experts, activating necessary modalities while "muting" irrelevant ones to maximize the signal-to-noise ratio. Extensive experiments on LongVideoBench and Video-MME across multiple MLLM backbones show that Q-Gate outperforms representative keyframe-selection baselines in most settings, with particularly strong gains on long and medium videos, providing a robust and interpretable solution for scalable video reasoning. Code is available at https://github.com/shaoguangwang/Q_Gate

查看此版本解读 →查看此版本原文 ↗