MEDR: Query-Independent Frame Selection via Multi-Signal Event Modeling and Dynamic Rescoring

[2608.15058] MEDR: Query-Independent Frame Selection via Multi-Signal Event Modeling and Dynamic Rescoring Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2608.15058 (cs) [Submitted on 15 Aug 2026] Title: MEDR: Query-Independent Frame Selection via Multi-Signal Event Modeling and Dynamic Rescoring Authors: Xinlei Pu , Weijie Shi , Wen Yang , Yi Cao , Hao Chen , Yuanjun Liu , Wenwei Ding , Jia Zhu , Jiajie Xu View a PDF of the paper titled MEDR: Query-Independent Frame Selection via Multi-Signal Event Modeling and Dynamic Rescoring, by Xinlei Pu and 8 other authors View PDF HTML (experimental) Abstract: Frame selection is a fundamental component of multimodal large language models, enabling long videos to be processed under limited visual-token and computational budgets. Uniform sampling preserves temporal coverage but may miss informative content that appears only briefly. To alleviate this limitation, query-dependent methods can retrieve question-relevant frames. However, because the selected frames depend on the current question, the same visual input cannot be directly shared across different questions, and frame selection must be repeated in multi-turn video dialogue. This motivates us to seek a query-independent frame selection method that preserves the reusability of a fixed visual input while improving the coverage of informative events beyond uniform sampling. We propose Multi-Signal Event Modeling and Dynamic Rescoring (MEDR), a training-free and query-independent frame selection method. Multi-Signal Event Modeling organizes complementary visual, motion, and text signals into signal-specific temporal events. Dynamic Rescoring then iteratively reevaluates each candidate relative to the current selected set, updating its score according to frame-level signal strength, additional event coverage, and temporal proximity. The resulting fixed frame set is constructed without observing the query and can be reused across different questions. On the standard benchmark evaluations, MEDR improves model accuracy by 0.63%-0.89% on Video-MME. On the long-video subset of LongVideoBench, it improves accuracy by up to 1.23% with Qwen3-VL-8B. MEDR further improves overall accuracy by 0.53%, while reusing exactly the same frame set for every question about a video. Comments: 9 pages, 2 figures, 3 tables Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.15058 [cs.CV] (or arXiv:2608.15058v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.15058 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Xinlei Pu [ view email ] [v1] Sat, 15 Aug 2026 06:10:43 UTC (2,070 KB) Full-text links: Access Paper: View a PDF of the paper titled MEDR: Query-Independent Frame Selection via Multi-Signal Event Modeling and Dynamic Rescoring, by Xinlei Pu and 8 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > 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? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• MEDR: Query-Independent Frame Selection via Multi-Signal Event Modeling and Dynamic Rescoring#611011
• Event-based Scene Synthesis via Inter-Frame Residual Alignment#1130496
• GleanVID: Complementary Token Selection for Efficient Video Large Language Models#1132243
• Less Is More: Genetic Frame Selection for Efficient Novel View Synthesis#1130229
• Query-aligned video frame selection for long video understanding#1115624