Graph Convolutional Networks Skeleton-based Action Recognition for Continuous Data Stream: A Sliding Window Approach

Mickael Delamare, Mickael Delamare, Cyril Laville, Adnane Cabani, Houcine Chafouk

2021

Abstract

This paper introduces a novel deep learning-based approach to human action recognition. The method consists of a Spatio-Temporal Graph Convolutional Network operating in real-time thanks to a sliding window approach. The proposed architecture consists of a fixed window for training, validation, and test process with a Spatio-Temporal-Graph Convolutional Network for skeleton-based action recognition. We evaluate our architecture on two available datasets of common continuous stream action recognition, the Online Action Detection dataset, and UOW Online Action 3D datasets. This method is utilized for temporal detection and classification of the performed action recognition in real-time.

Paper Citation

in Harvard Style

Delamare M., Laville C., Cabani A. and Chafouk H. (2021). Graph Convolutional Networks Skeleton-based Action Recognition for Continuous Data Stream: A Sliding Window Approach. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 427-435. DOI: 10.5220/0010234904270435

in Bibtex Style

@conference{visapp21,
author={Mickael Delamare and Cyril Laville and Adnane Cabani and Houcine Chafouk},
title={Graph Convolutional Networks Skeleton-based Action Recognition for Continuous Data Stream: A Sliding Window Approach},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={427-435},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010234904270435},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Graph Convolutional Networks Skeleton-based Action Recognition for Continuous Data Stream: A Sliding Window Approach
SN - 978-989-758-488-6
AU - Delamare M.
AU - Laville C.
AU - Cabani A.
AU - Chafouk H.
PY - 2021
SP - 427
EP - 435
DO - 10.5220/0010234904270435
PB - SciTePress