Geometric Deep Learning on Skeleton Sequences for 2D/3D Action Recognition

Rasha Friji, Rasha Friji, Hassen Drira, Faten Chaieb

2020

Abstract

Deep Learning models, albeit successful on data defined on Euclidean domains, are so far constrained in many fields requiring data which underlying structure is a non-Euclidean space, namely computer vision and imaging. The purpose of this paper is to build a geometry aware deep learning architecture for skeleton based action recognition. In this perspective, we propose a framework for non-Euclidean data classification based on 2D/3D skeleton sequences, specifically for Parkinson's disease classification and action recognition. As a baseline, we first design two Euclidean deep learning architectures without considering the Riemannian structure of the data. Then, we introduce new architectures that extend Convolutional Neural Networks (CNNs) and Recurrent Neural Networks(RNNs) to non-Euclidean data. Experimental results show that our method outperforms state-of-the-art performances for 2D abnormal behavior classification and 3D human action recognition.

Paper Citation

in Harvard Style

Friji R., Drira H. and Chaieb F. (2020). Geometric Deep Learning on Skeleton Sequences for 2D/3D Action Recognition. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 196-204. DOI: 10.5220/0009161701960204

in Bibtex Style

@conference{visapp20,
author={Rasha Friji and Hassen Drira and Faten Chaieb},
title={Geometric Deep Learning on Skeleton Sequences for 2D/3D Action Recognition},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={196-204},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009161701960204},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - Geometric Deep Learning on Skeleton Sequences for 2D/3D Action Recognition
SN - 978-989-758-402-2
AU - Friji R.
AU - Drira H.
AU - Chaieb F.
PY - 2020
SP - 196
EP - 204
DO - 10.5220/0009161701960204
PB - SciTePress