Learning Video Alignment for Unsupervised Temporal Action Segmentation
IEEE Transactions on Circuits and Systems for Video Technology · 2026-07 · 36 (7) · 9876-9887
DOI: 10.1109/tcsvt.2026.3672129 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-07. Verfasst von Xianan Xie und 3 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Unsupervised temporal action segmentation is a critical yet challenging task in high-level video understanding, which aims to partition continuous, untrimmed videos into distinct action segments without relying on manual annotations during the training phase. Existing methods typically exploit pre-extracted features for clustering or boundary detection but often suffer from limited accuracy and scalability. In this paper, we reframe unsupervised temporal action segmentation as a video alignment learning task and propose a novel framework with a Frame-Segment Contrastive (FSC) loss. The FSC loss simultaneously encourages fine-grained frame-level alignment and global segment-level coherence, effectively capturing temporal structures in a fully label-free manner. To map the learned representations to semantic categories, we introduce an inference-time exemplar-based label transfer strategy. This approach utilizes the alignment path from a single labeled reference video to generate predictions for target videos. Extensive experiments conducted on five benchmark datasets—Pouring, Penn Action, Breakfast, IKEA Assembly, and Desktop Assembly—demonstrate that our method outperforms state-of-the-art approaches, validating its robustness and scalability in modeling complex temporal dependencies.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Xie, X., Sheng, Y., Liu, H., & Li, J. (2026). Learning Video Alignment for Unsupervised Temporal Action Segmentation. IEEE Transactions on Circuits and Systems for Video Technology, 36(7), 9876-9887. https://doi.org/10.1109/tcsvt.2026.3672129
Vancouver
Xie X, Sheng Y, Liu H, Li J. Learning Video Alignment for Unsupervised Temporal Action Segmentation. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(7):9876-9887. doi:10.1109/tcsvt.2026.3672129
BibTeX
@article{Xie2026,
author = {Xie, Xianan and Sheng, Yuanyuan and Liu, Huanyu and Li, Junbao},
title = {Learning Video Alignment for Unsupervised Temporal Action Segmentation},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {7},
pages = {9876--9887},
doi = {10.1109/tcsvt.2026.3672129}
}
EUVIMED