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 convolutional autoencoder that uses graph Laplacian regularization to model the skeletal geometry across the temporal dynamics of actions. Our approach is robust towards viewpoint variations by including a self-supervised gradient reverse layer that ensures generalization 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 approaches on the cross-subject, cross-view, and cross-setup protocols. Although unsupervised, 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

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

C. Beyan;A. Del Bue
2021-01-01

Abstract

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 convolutional autoencoder that uses graph Laplacian regularization to model the skeletal geometry across the temporal dynamics of actions. Our approach is robust towards viewpoint variations by including a self-supervised gradient reverse layer that ensures generalization 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 approaches on the cross-subject, cross-view, and cross-setup protocols. Although unsupervised, 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
2021
action recognition, autoencoder, skeletal data, unsupervised feature learning
File in questo prodotto:
File Dimensione Formato  
IC22_Unsupervised Human Action Recognition.pdf

accesso aperto

Tipologia: Versione dell'editore
Licenza: Creative commons
Dimensione 8.58 MB
Formato Adobe PDF
8.58 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/1121906
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? ND
social impact