Query-Aware Video Frame Selection

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 133% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 36

All topics

VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding
May 7, 2026Kuanwei Lin, Wenhao Zhang, Ge LiEfficient VLM Inference Long-Video Understanding
School of Electronic and Computer Engineering, Peking University
VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA
May 6, 2026Haibin He, Maoyuan Ye, Jing Zhang +2Video QA Video Frame Selection
School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, Hubei, China
Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models
May 3, 2026Martin Q. Ma, Willis Guo, Aditya Agrawal +4Active Perception Efficient VLM Inference
Carnegie Mellon University · MIT
Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding
Apr 19, 2026Shaoguang Wang, Weiyu Guo, Ziyang Chen +2Multimodal Large Language Models Multimodal QA
Thrust of Artificial Intelligence, HKUST (Guangzhou) Guangzhou, China · Department of CSE, HKUST Hong Kong SAR, China
HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering
Mar 19, 2026Dan Ben-Ami, Gabriele Serussi, Kobi Cohen +1Multimodal Large Language Models Multimodal QA
INSIGHT Lab, Ben-Gurion University of the Negev, Israel · Ben-Gurion University of the Negev, Israel
FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering
Mar 4, 2026Tatiana Zemskova, Solomon Andryushenko, Ilya Obrubov +4Efficient VLM Inference Egocentric Video QA
AXXX · MIRAI · Yandex +1

May 7, 2026, cs.CVJ/K move · Enter open · S save

VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding

Kuanwei Lin, Wenhao Zhang, Ge Li

School of Electronic and Computer Engineering, Peking University

Efficient VLM Inference Long-Video Understanding Video Token Compression Visual Token Compression Query-Aware Video Frame Selection

Open paper AskPDF arXiv

Video large multimodal models increasingly face a scalability bottleneck: long videos produce excessively long visual-token sequences, which sharply increase memory and latency during inference. While existing compression methods are effective in specific settings, most are either weakly query-aware or apply a fixed compression policy across frames, proving suboptimal when visual evidence is unevenly distributed over time. To address this, we present VideoRouter, a query-adaptive dual-router framework built on InternVL for budgeted evidence allocation. The Semantic Router predicts the dominant allocation policy, choosing between broad temporal coverage and adaptive high-resolution preservation, while the Image Router uses early LLM layers to score frame relevance. This enables aggressive compression on less relevant frames while preserving detail on critical evidence frames. To train both routers, we build Video-QTR-10K for allocation-policy supervision and Video-FLR-200K for frame-relevance supervision. Experiments on VideoMME, MLVU, and LongVideoBench show that VideoRouter consistently improves over the InternVL baseline under comparable or lower budgets, achieving up to a 67.9% token reduction.

Momentum

Related topics

Latest papers 36

VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding

VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA

Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models

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

HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering

FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering