English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper presents a novel end-to-end method for the problem ofskeleton-based unsupervised human action recognition. We propose a newarchitecture with a convolutional autoencoder that uses graph Laplacianregularization to model the skeletal geometry across the temporal dynamics ofactions. Our approach is robust towards viewpoint variations by including aself-supervised gradient reverse layer that ensures generalization acrosscamera views. The proposed method is validated on NTU-60 and NTU-120large-scale datasets in which it outperforms all prior unsupervisedskeleton-based approaches on the cross-subject, cross-view, and cross-setupprotocols. Although unsupervised, our learnable representation allows ourmethod even to surpass a few supervised skeleton-based action recognitionmethods. 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