Metraipolis › archive › dc_042e617e092a

Boundary Voting Network for Ambiguity-Aware Timestamp-Supervised Action Segmentation — arXiv:2609.08167

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08167
License (as archived)
CC0-1.0
Archived
2026-10-16T15:12:05.375Z
SHA-256 of the archived text
5720d3392c2140c76a5a3b36040916a0b6511a60fcc2da2a14e47128219f1087
Stable URL of this page
https://metraipolis.com/documento/dc_042e617e092a

How to cite

Boundary Voting Network for Ambiguity-Aware Timestamp-Supervised Action Segmentation — arXiv:2609.08167 — arXiv (en), https://arxiv.org/abs/2609.08167 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_042e617e092a (Metraipolis archive dc_042e617e092a, sha256 5720d3392c2140c76a5a3b36040916a0b6511a60fcc2da2a14e47128219f1087)
BibTeX
@misc{dc042e617e092a,
  title = {Boundary Voting Network for Ambiguity-Aware Timestamp-Supervised Action Segmentation — arXiv:2609.08167},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08167},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_042e617e092a; sha256 5720d3392c2140c76a5a3b36040916a0b6511a60fcc2da2a14e47128219f1087},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08167. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Timestamp-supervised action segmentation aims to segment and classify actions in untrimmed videos with a random frame annotated per action. Precisely localizing action boundaries from timestamp annotations is crucial for this setting, as it enables generating framewise pseudo-labels and applying the well-explored fully-supervised training. However, prevailing methods struggle with intrinsic uncertainty in boundary localization due to less discriminative features in action-transiting regions. This imprecise boundary estimation significantly reduces the stability and reliability of the generated pseudo-labels in ambiguous action-transiting regions, consequently resulting in performance deterioration of the trained segmentation models. In our paper, we introduce the boundary voting network that mitigates feature ambiguity by hierarchically propagating video-level global prior knowledge into local action-transiting regions. By generating key action representations as votes throughout the video and targeting action-transiting regions, all votes collaboratively contribute to action-transiting feature enhancement and boundary localization refinement. Extensive experiments demonstrate the effectiveness of our method on GTEA, 50Salads, and Breakfast datasets.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.08167 — 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 2026-10-16T14:49:57.283Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).