# Query-aligned video frame selection for long video understanding

arXiv: https://arxiv.org/abs/2609.31668 · HTML: https://mlsanity.com/paper/2609.31668/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 20 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models](https://mlsanity.com/paper/2311.07575/) (2023)
- [Adaptive Keyframe Sampling for Long Video Understanding](https://mlsanity.com/paper/2502.21271/) (2025)
- [LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token](https://mlsanity.com/paper/2501.03895/) (2025)
- [Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs](https://mlsanity.com/paper/2506.22139/) (2025)
- [KeyVideoLLM: Towards Large-scale Video Keyframe Selection](https://mlsanity.com/paper/2407.03104/) (2024)
- [FOCUS: Efficient Keyframe Selection for Long Video Understanding](https://mlsanity.com/paper/2510.27280/) (2025)
- [VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding](https://mlsanity.com/paper/2312.02310/) (2023)

## Abstract (arXiv)

Multimodal large language models (MLLMs) process multimodal inputs by converting text, images, and videos into token sequences that are subsequently processed by a backbone language model. While MLLMs have achieved excellent performance in understanding the content of individual images, video understanding remains significantly more difficult because videos contain large number of video frames. MLLMs typically process only a subset of these frames, usually ranging from 8 to 64. MLLMs usually sample frames uniformly, regardless of their relevance to the question being answered. To address this limitation, several training-free, model-agnostic methods for selecting question-relevant frames have recently been proposed. In this work, we introduce a frame-selection method designed specifically for multiple-choice questions. We extend the query text by appending semantic cues derived from the answer choices and employ a direct query-frame alignment scoring mechanism. To the best of our knowledge, our method is the first to directly utilize answer choices as inference-time cues for selecting frames relevant to answering a question. The method first constructs a compact candidate pool by subsampling video frames at a fixed rate. The frames are then scored according to their maximum cosine similarity across all question-answer pairs to identify the most relevant frames for a given query. This approach preserves a fixed token budget while improving the relevance of the visual evidence provided to the downstream MLLM. We evaluate the effectiveness of our frame-selection method on the MLVU, Video-MME, and LongVideoBench benchmarks using three MLLMs: LLaVA-Mini, Qwen2-VL, and LLaVA-Video. Experimental results demonstrate that answer-aware frame selection generally outperforms uniform sampling and existing training-free frame-selection methods under the same frame budget.