# Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering Source: [Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:36:41.717Z Authors: Yumeng Shi, Quanyu Long, Wenya Wang Published: 2025-04-30T08:03:54.000Z ## Abstract Video question answering benefits from the rich information in videos, enabling various applications. However, the large volume of tokens generated from long videos presents challenges to memory efficiency and model performance. To alleviate this, existing works propose to compress video inputs, but often overlook the varying importance of static and dynamic information across different queries, leading to inefficient token usage within limited budgets. We propose a novel token selection strategy, \\textsc{explore-then-select}, that adaptively adjusts static and dynamic information based on question requirements. Our framework first explores different token allocations between key frames, which preserve spatial details, and delta frames, which capture temporal changes. Then it employs a query-aware attention-based metric to select the optimal token combination without model updates. Our framework is plug-and-play and can be seamlessly integrated within diverse video language models. Extensive experiments show that our method achieves significant performance improvements (up to 5.8\\%) on multiple video question answering benchmarks. Our code is available at https://github.com/ANDgate99/Explore-Then-Select . ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()