超越帧选择：用多模态大语言模型重新思考长视频理解

Computer Science > Computer Vision and Pattern Recognition arXiv:2608.05592 (cs) [Submitted on 6 Aug 2026 (v1), last revised 9 Sep 2026 (this version, v2)] Title:Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs Authors:Ziling Huang, Shin'ichi Satoh View a PDF of the paper titled Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs, by Ziling Huang and 1 other authors View PDF HTML (experimental) Abstract:Multimodal Large Language Models (MLLMs) have made strong progress in video understanding, yet long videos remain difficult: the visual token budget grows with video length, so temporally sparse evidence is easily lost. Existing methods compress the input through uniform sampling or frame selection, but these strategies optimize different objectives, either broad temporal coverage or local question relevance, and neither preserves both global storyline context and fine-grained evidence. We propose VideoRouter (VR), which rethinks long-video understanding as coordinating complementary evidence views rather than selecting a single subset of frames. VideoRouter first organizes each video into a question-agnostic temporal hierarchy that partitions it into coarse-to-fine temporally coherent segments. Upper-level nodes capture broad storyline context and event progression, while lower-level nodes preserve fine-grained local details and evidence-bearing moments. This gives rise to two complementary views: a global view for coverage-oriented reasoning and a local view for detail-oriented evidence recovery. We further introduce a verification-guided router that judges which view is better supported by its own selected evidence and decides the final answer. Across six backbones, routing improves over both views in all settings, and the choice of view is shown to be dataset-dependent, confirming that no single evidence granularity is universally preferable. On VideoMME, our method outperforms state-of-the-art frame selection methods by 2.5 points, under the LLaVA-Video-7B backbone. We will release the code. Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.05592 [cs.CV] (or arXiv:2608.05592v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.05592 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ziling Huang [view email] [v1] Thu, 6 Aug 2026 04:27:59 UTC (1,311 KB) [v2] Wed, 9 Sep 2026 14:22:13 UTC (2,021 KB) Full-text links: Access Paper: View a PDF of the paper titled Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs, by Ziling Huang and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)