Vision-language models (VLMs) advance video understanding but operate under tight computational budgets, making performance dependent on selecting a small, high-quality subset of frames. Existing frame sampling strategies, such as uniform or fixed-budget selection, fail to adapt to variations in content density or task complexity. To address this, we present FrameOracle, a lightweight, plug-and-play module that predicts both (1) which frames are most relevant to a given query and (2) how many frames are needed. FrameOracle is trained via a curriculum that progresses from weak proxy signals, such as cross-modal similarity, to stronger supervision with FrameOracle-41K, the first large-scale VideoQA dataset with validated keyframe annotations specifying minimal sufficient frames per question. Extensive experiments across five VLMs and six benchmarks show that FrameOracle reduces 16-frame inputs to an average of 10.4 frames without accuracy loss. When starting from 64-frame candidates, it reduces inputs to 13.9 frames on average while improving accuracy by 1.5%, achieving state-of-the-art efficiency-accuracy trade-offs for scalable video understanding.
@article{arxiv.2510.03584,
title = {FrameOracle: Learning What to See and How Much to See in Videos},
author = {Chaoyu Li and Tianzhi Li and Fei Tao and Zhenyu Zhao and Ziqian Wu and Maozheng Zhao and Juntong Song and Cheng Niu and Pooyan Fazli},
journal= {arXiv preprint arXiv:2510.03584},
year = {2026}
}