Metraipolis › archive › dc_afa6aff08c39
Query-aligned video frame selection for long video understanding — arXiv:2609.31668
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31668
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:59:20.116Z
- SHA-256 of the archived text
0362f8969a4004d2cfe956c90c4d80ede31839d8e5eb21ac76dc240cc5413288- Stable URL of this page
https://metraipolis.com/documento/dc_afa6aff08c39
How to cite
Query-aligned video frame selection for long video understanding — arXiv:2609.31668 — arXiv (en), https://arxiv.org/abs/2609.31668 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_afa6aff08c39 (Metraipolis archive dc_afa6aff08c39, sha256 0362f8969a4004d2cfe956c90c4d80ede31839d8e5eb21ac76dc240cc5413288)
BibTeX
@misc{dcafa6aff08c39,
title = {Query-aligned video frame selection for long video understanding — arXiv:2609.31668},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31668},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_afa6aff08c39; sha256 0362f8969a4004d2cfe956c90c4d80ede31839d8e5eb21ac76dc240cc5413288},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31668. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.31668 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:02.011Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).