Metraipolis › archive › dc_520b97ba0e02

Multi-Scale Temporal Domain Alignment for Federated Video Domain Adaptation — arXiv:2608.29186

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29186
License (as archived)
CC0-1.0
Archived
2026-10-17T09:53:44.988Z
SHA-256 of the archived text
fcf8975ce2ca9222678bebe677be0f8cc401bf29456dea133c83a8c7aa27bc65
Stable URL of this page
https://metraipolis.com/documento/dc_520b97ba0e02

How to cite

Multi-Scale Temporal Domain Alignment for Federated Video Domain Adaptation — arXiv:2608.29186 — arXiv (en), https://arxiv.org/abs/2608.29186 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_520b97ba0e02 (Metraipolis archive dc_520b97ba0e02, sha256 fcf8975ce2ca9222678bebe677be0f8cc401bf29456dea133c83a8c7aa27bc65)
BibTeX
@misc{dc520b97ba0e02,
  title = {Multi-Scale Temporal Domain Alignment for Federated Video Domain Adaptation — arXiv:2608.29186},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29186},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_520b97ba0e02; sha256 fcf8975ce2ca9222678bebe677be0f8cc401bf29456dea133c83a8c7aa27bc65},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29186. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated Video Domain Adaptation (FVDA) enables collaborative learning across distributed and non-IID video datasets while preserving privacy, but is under-explored due to challenges in aligning temporal information. We propose Multi-scalE Temporal domAin aLignment (METAL), a novel framework that leverages temporal information at multiple resolutions to improve cross-domain video action recognition with only model parameter transfers. METAL trains per-scale transformer encoders on source-clients, then performs independent knowledge voting at each temporal scale to generate robust pseudo-labels on the target-server. A novel $L_2$ variance penalty enforces cross-scale consistency during scale-based knowledge distillation, preventing a singular dominant scale. The late fusion aggregates features across different scales, where the fusion head is trained via knowledge distillation using confidence-weighted aggregation of scale-wise predictions, enabling the model to effectively exploit complementary temporal information for final predictions. Experiments on Epic-Kitchens-55 and Daily-DA demonstrate state-of-the-art performances, with gains up to 28.47% over current FDA methods. Ablation studies prove that multi-scale distillation and scale coordination are critical for effective temporal knowledge transfer.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.29186 — 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 2026-10-17T09:28:47.998Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).