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 / Paoletti, Giancarlo; Cavazza, Jacopo; Beyan, Cigdem; Del Bue, Alessio. - ELETTRONICO. - (2021), pp. 1-13. (Intervento presentato al convegno BMVC tenutosi a Virtual nel 22nd- 25th November 2021).
Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance
Beyan Cigdem;
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_LaplacianFile | Dimensione | Formato | |
---|---|---|---|
IC22_Unsupervised Human Action Recognition.pdf
accesso aperto
Tipologia:
Post-print referato (Refereed author’s manuscript)
Licenza:
Tutti i diritti riservati (All rights reserved)
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