Metraipolis › archive › dc_f6a533c8b1bb
FIS-OT: Feature-Induced Optimal Transport for Unsupervised Action Segmentation — arXiv:2608.29980
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29980
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:59:16.592Z
- SHA-256 of the archived text
bc6c8e626b526a176f9a4cc0686bac73fba5ad6d57c697e4a960e6c2ea8bd507- Stable URL of this page
https://metraipolis.com/documento/dc_f6a533c8b1bb
How to cite
FIS-OT: Feature-Induced Optimal Transport for Unsupervised Action Segmentation — arXiv:2608.29980 — arXiv (en), https://arxiv.org/abs/2608.29980 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f6a533c8b1bb (Metraipolis archive dc_f6a533c8b1bb, sha256 bc6c8e626b526a176f9a4cc0686bac73fba5ad6d57c697e4a960e6c2ea8bd507)
BibTeX
@misc{dcf6a533c8b1bb,
title = {FIS-OT: Feature-Induced Optimal Transport for Unsupervised Action Segmentation — arXiv:2608.29980},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29980},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f6a533c8b1bb; sha256 bc6c8e626b526a176f9a4cc0686bac73fba5ad6d57c697e4a960e6c2ea8bd507},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29980. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Unsupervised action segmentation is a challenging task. It involves finding action categories and boundaries in videos without labels. Existing Optimal Transport (OT) methods use global constraints. This causes them to overlook the use of local information. Furthermore, existing Optimal transport architectures are prone to confirmation bias because they overly trust the pseudo-labels they generate. This causes models to learn from noise in the early training stages. To address these issues, we propose FIS-OT. It is a novel Feature-Induced Structured Optimal Transport framework. First, we introduce a Feature Enhanced Generator (FEG) module. It serves as an internal regularizer. By using triplet loss, FEG captures local consistency. It provides robust supervision that is independent of noisy pseudo-labels. Second, we propose a Feature-Induced Residual Structural Prior. This combines a fixed temporal backbone with dynamic feature similarities. This design ensures temporal continuity. It also allows the solver to adapt to complex action structures. Finally, we establish a cyclic optimization loop. This aligns local feature learning with global structural alignment. Extensive experiments on the three datasets show the effectiveness of our method. 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/2608.29980 — 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 2026-10-17T09:28:48.098Z 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).