Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance

This paper presents a novel end-to-end method for the problem of skeleton-based unsupervised human action recognition. We propose a new architecture with a convolu- tional autoencoder that uses graph Laplacian regularization to model the skeletal geom- etry across the temporal dynamics of actions. Our approach is robust towards viewpoint variations by including a self-supervised gradient reverse layer that ensures generaliza- tion across camera views. The proposed method is validated on NTU-60 and NTU-120 large-scale datasets in which it outperforms all prior unsupervised skeleton-based ap- proaches on the cross-subject, cross-view, and cross-setup protocols. Although unsuper- vised, our learnable representation allows our method even to surpass a few supervised skeleton-based action recognition methods. The code is available in: www.github. com/IIT-PAVIS/UHAR_Skeletal_Laplacian