ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA
Abstract
ReQuest is an uncertainty-driven, question-adaptive keyframe selection pipeline that improves long-video question answering by selectively computing and routing based on model uncertainty without fine-tuning the underlying multimodal large language model.
Recent multimodal large language models (MLLMs) have substantially advanced video understanding, yet long-form video QA remains challenging under fixed input token budgets, where uniform sampling can be inefficient for evidence localization. We propose ReQuest , an uncertainty-driven, question-adaptive keyframe selection pipeline that aligns question intent with relevant video content through selective computation. ReQuest integrates (i) a lightweight question-aware selector distilled from MLLM-generated supervision, (ii) Re-thinking Routing that triggers additional inference only when the model is uncertain with a length-adaptive criterion, and (iii) uncertainty-guided adaptive non-maximum suppression that selects temporally diverse frames while adjusting spacing based on question difficulty. As a plug-andplay method, ReQuest improves long-video QA without modifying or fine-tuning the underlying MLLM. Experiments on Video-MME, MLVU, and LongVideoBench demonstrate consistent accuracy gains with competitive computational cost, with particularly strong improvements in medium and long video regimes.
Get this paper in your agent:
hf papers read 2607.01737 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 1
Datasets citing this paper 1
suyong-3/ReQuest
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper