Contrast-Reconstruction Representation Learning for Self-Supervised Skeleton-Based Action Recognition

Skeleton-based action recognition is widely used in varied areas, e.g., surveillance and human-machine interaction. Existing models are mainly learned in a supervised manner, thus heavily depending on large-scale labeled data, which could be infeasible when labels are prohibitively expensive. In thi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 23., Seite 6224-6238
1. Verfasser:	Wang, Peng (VerfasserIn)
Weitere Verfasser:	Wen, Jun, Si, Chenyang, Qian, Yuntao, Wang, Liang
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2022
Zugriff auf das übergeordnete Werk:	IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:	Journal Article