Metraipolis › archive › dc_a279b92bc418
CueKFS: Agentic Cue-Driven Keyframe Selection for Long Video Understanding — arXiv:2609.31873
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31873
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:59:36.395Z
- SHA-256 of the archived text
213b669ab7fb8578bc6ed4aa70b52a5071dff730c4d521deacbff8c49bcfb318- Stable URL of this page
https://metraipolis.com/documento/dc_a279b92bc418
How to cite
CueKFS: Agentic Cue-Driven Keyframe Selection for Long Video Understanding — arXiv:2609.31873 — arXiv (en), https://arxiv.org/abs/2609.31873 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a279b92bc418 (Metraipolis archive dc_a279b92bc418, sha256 213b669ab7fb8578bc6ed4aa70b52a5071dff730c4d521deacbff8c49bcfb318)
BibTeX
@misc{dca279b92bc418,
title = {CueKFS: Agentic Cue-Driven Keyframe Selection for Long Video Understanding — arXiv:2609.31873},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31873},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a279b92bc418; sha256 213b669ab7fb8578bc6ed4aa70b52a5071dff730c4d521deacbff8c49bcfb318},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31873. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Keyframe selection (KFS) has long produced compact video summaries for browsing and retrieval, and representative frames for thumbnails. More recently, when conditioned on a question, KFS provides an alternative to uniform sampling for long-video question answering by selecting frames that are more relevant to the question. Most methods rank frames by similarity to the question. Yet a relevant frame may score poorly when the question combines subjects or moments that no single frame shows, or requires implicit information absent from its wording. Other methods try to break down the question into subqueries, but suffer from inaccurate decomposition due to their static initial context. Therefore, we propose CueKFS, a training-free method that reformulates question--frame matching as comparing frames against a set of dynamically generated visual cues. From an initial set of salient frames, we decompose the question into cues. Each cue concurrently probes the video to navigate to its own evidence. A reasoning VLM then agentically revises the cue set against its evidence to re-explore the video. CueKFS then allocates the budget across the surviving cues. Across three benchmarks, CueKFS establishes state-of-the-art results in all 27 evaluated settings with available prior results, achieving budget-averaged gains of up to +4.54% over the previous baseline and a median of only two VLM calls. We further provide a detailed behavioral analysis of CueKFS, showing that agentic cue refinement drives active re-exploration of the video, yielding relative similarity gains of up to 92% over the initial context. 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); Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.31873 — 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 2026-10-07T20:29:02.161Z 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).