EUVIMEDEUVIMED entdecken
Crossref

Self-Supervised Skeleton Representation Learning Via Actionlet Contrast and Reconstruct

Lilang Lin, Jiahang Zhang, Jiaying Liu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-11 · 47 (11) · 10818-10835

DOI: 10.1109/tpami.2025.3598138 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-11. Verfasst von Lilang Lin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: Program of Beijing Municipal Science and Technology Commission Foundation, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Contrastive learning has shown remarkable success in the domain of skeleton-based action recognition. However, the design of data transformations, which is crucial for effective contrastive learning, remains a challenging aspect in the context of skeleton-based action recognition. The difficulty lies in creating data transformations that capture rich motion patterns while ensuring that the transformed data retains the same semantic information. To tackle this challenge, we introduce an innovative framework called ActCLR+ (Actionlet-Dependent Contrastive Learning), which explicitly distinguishes between static and dynamic regions in a skeleton sequence. We begin by introducing the concept of actionlet, connecting self-supervised learning quantitatively with downstream tasks. Actionlets represent regions in the skeleton where features closely align with action prototypes, highlighting dynamic sequences as distinct from static ones. We propose an anchor-based method for unsupervised actionlet discovery, establishing a motion-adaptive data transformation approach based on this discovery. This motion-adaptive data transformation strategy tailors data transformations for actionlet and non-actionlet regions, respectively, introducing more diverse motion patterns while preserving the original motion semantics. Additionally, we incorporate a semantic-aware masked motion modeling technique to enhance the learning of actionlet representations. Our comprehensive experiments on well-established benchmark datasets such as NTU RGB+D and PKUMMD validate the effectiveness of our proposed method.

Förderung

  • Program of Beijing Municipal Science and Technology Commission Foundation
  • National Natural Science Foundation of China

Zitieren

APA

Lin, L., Zhang, J., & Liu, J. (2025). Self-Supervised Skeleton Representation Learning Via Actionlet Contrast and Reconstruct. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(11), 10818-10835. https://doi.org/10.1109/tpami.2025.3598138

Vancouver

Lin L, Zhang J, Liu J. Self-Supervised Skeleton Representation Learning Via Actionlet Contrast and Reconstruct. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(11):10818-10835. doi:10.1109/tpami.2025.3598138

BibTeX
@article{Lin2025,
  author = {Lin, Lilang and Zhang, Jiahang and Liu, Jiaying},
  title = {Self-Supervised Skeleton Representation Learning Via Actionlet Contrast and Reconstruct},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {11},
  pages = {10818--10835},
  doi = {10.1109/tpami.2025.3598138}
}
Kostenlos starten →