Metraipolis › archive › dc_ca7747bbb5f2

Efficient Video Dataset Distillation via Cluster-Guided Prototype Blending — arXiv:2608.03269

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03269
License (as archived): CC0-1.0
Archived: 2026-10-31T12:18:43.542Z
SHA-256 of the archived text: 3bb270d1a260081845745d77a2d28eea092f126ca466490130c15ccfe2af197e
Stable URL of this page: https://metraipolis.com/documento/dc_ca7747bbb5f2

How to cite

Efficient Video Dataset Distillation via Cluster-Guided Prototype Blending — arXiv:2608.03269 — arXiv (en), https://arxiv.org/abs/2608.03269 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca7747bbb5f2 (Metraipolis archive dc_ca7747bbb5f2, sha256 3bb270d1a260081845745d77a2d28eea092f126ca466490130c15ccfe2af197e)

BibTeX

@misc{dcca7747bbb5f2,
  title = {Efficient Video Dataset Distillation via Cluster-Guided Prototype Blending — arXiv:2608.03269},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03269},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca7747bbb5f2; sha256 3bb270d1a260081845745d77a2d28eea092f126ca466490130c15ccfe2af197e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03269. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Video dataset distillation aims to compress a large video dataset into a compact surrogate set that preserves its training utility. Most existing approaches synthesize condensed videos through iterative optimization, whose cost is amplified by the temporal dimension. Rather than further reducing the number of optimized variables, we investigate whether effective distilled videos can be constructed without gradient-based optimization of the stored videos. Such a construction-based approach must address three challenges: selecting informative temporal segments, covering diverse intra-class variations under a limited videos-per-class budget, and increasing the information carried by each stored sample. To this end, we propose ProtoBlend, an efficient select-allocate-blend framework. First, teacher-guided temporal clip selection retains a high-confidence segment from each source video. Second, cluster-guided prototype allocation partitions the selected clips in the teacher feature space and assigns one distilled slot to each intra-class cluster. Third, each prototype is blended with an in-cluster anchor, while their teacher predictions are combined using the same coefficient to provide mixture-source supervision. Experiments on four trimmed action-recognition benchmarks demonstrate that ProtoBlend achieves a competitive accuracy-efficiency trade-off without iterative optimization of the distilled videos.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03269 — 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 2026-10-31T12:05:53.025Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).