Metraipolis › archive › dc_edeac26be19b

MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding — arXiv:2609.15408

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15408
License (as archived)
CC0-1.0
Archived
2026-10-15T23:17:15.354Z
SHA-256 of the archived text
614559339abad93582c719052b0ba44f53260db4f80300a576239f05a55df3ef
Stable URL of this page
https://metraipolis.com/documento/dc_edeac26be19b

How to cite

MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding — arXiv:2609.15408 — arXiv (en), https://arxiv.org/abs/2609.15408 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edeac26be19b (Metraipolis archive dc_edeac26be19b, sha256 614559339abad93582c719052b0ba44f53260db4f80300a576239f05a55df3ef)
BibTeX
@misc{dcedeac26be19b,
  title = {MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding — arXiv:2609.15408},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15408},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edeac26be19b; sha256 614559339abad93582c719052b0ba44f53260db4f80300a576239f05a55df3ef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15408. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-video understanding remains challenging for multimodal large language models (MLLMs) because densely encoding long frame sequences is computationally expensive, while uniform sampling under a limited visual budget can miss sparse yet decisive evidence. Recent training-free keyframe selection methods have enabled more efficient inference and yielded promising performance gains. However, many existing methods score frames largely in isolation without explicitly considering how each candidate complements the currently selected subset, potentially resulting in redundant selections and incomplete evidence coverage. To address this limitation, we propose MarKey, a training-free framework that formulates keyframe selection as subset-aware greedy optimization. At each iteration, MarKey scores each candidate using a tractable surrogate that jointly accounts for query relevance, marginal coverage gain, and context-dependent redundancy, and selects the frame with the highest utility. To make this iterative subset-aware evaluation efficient, MarKey uses a compact set of representative anchors to approximate full-video coverage and a bounded window of previously selected frames to limit context-dependent comparisons. Experiments on six benchmarks spanning holistic video understanding, human-centric video understanding, and open-ended video understanding demonstrate that MarKey consistently outperforms existing methods. Further analyses show robust gains across different MLLM backbones, model scales, and frame budgets.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.15408 — 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 2026-10-15T22:51:10.036Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).