Metraipolis › archive › dc_8a1e39873d23

See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learning — arXiv:2608.29611

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29611
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:03.190Z
SHA-256 of the archived text
e74840cea50c128ab88ab16beb4a46c019d20a68507c839a1de90dcfe4d7dd9e
Stable URL of this page
https://metraipolis.com/documento/dc_8a1e39873d23

How to cite

See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learning — arXiv:2608.29611 — arXiv (en), https://arxiv.org/abs/2608.29611 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a1e39873d23 (Metraipolis archive dc_8a1e39873d23, sha256 e74840cea50c128ab88ab16beb4a46c019d20a68507c839a1de90dcfe4d7dd9e)
BibTeX
@misc{dc8a1e39873d23,
  title = {See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learning — arXiv:2608.29611},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29611},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a1e39873d23; sha256 e74840cea50c128ab88ab16beb4a46c019d20a68507c839a1de90dcfe4d7dd9e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29611. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Unsupervised action segmentation aims to discover latent action categories and their temporal organization without action annotations. Optimal transport-based methods provide structured frame-to-action assignments, however, their pseudo-label quality is fundamentally conditioned on the representation space used to construct the transport cost. We argue that reliable OT pseudo-labeling requires a representation geometry that is simultaneously sensitive to discriminative action changes and coherent along local temporal progressions. Based on this insight, we propose SpecT-OT, a spectral-temporal representation learning framework built upon an unbalanced optimal transport pseudo-labeling concept. SpecT-OT introduces a Spectral Reparameterization Projector (SRP), which parameterizes projector weights with fixed Fourier bases and learnable coefficients to improve the modeling of rapidly varying discriminative features, and Temporal Affinity Regularization (TAR), which imposes distance-aware, label-free constraints on pairwise frame affinities to stabilize local temporal structure. The two components jointly produce more discriminative and temporally stable transport costs, yielding more reliable pseudo-labels for iterative representation learning. Experiments on four benchmarks demonstrate strong performance compared with state-of-the-art methods. SpecT-OT achieves the best results on 13 of 15 metrics, including 4.1-point MoF and 7.4-point F1 gains over the baseline on Breakfast and Desktop Assembly, respectively.

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/2608.29611 — 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 2026-10-17T09:28:48.053Z 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).