An Extensible Deep Architecture for Action Recognition Problem

Isaac Sanou, Donatello Conte, Hubert Cardot

2019

Abstract

Human action Recognition has been extensively addressed by deep learning. However, the problem is still open and many deep learning architectures show some limits, such as extracting redundant spatio-temporal informations, using hand-crafted features, and instability of proposed networks on different datasets. In this paper, we present a general method of deep learning for the human action recognition. This model fits on any type of database and we apply it on CAD-120 which is a complex dataset. Our model thus clearly improves in two aspects. The first aspect is on the redundant informations and the second one is the generality and the multi-functionality application of our deep architecture. Our model uses only raw data for human action recognition and the approach achieves state-of-the-art action classification performance.

Paper Citation

in Harvard Style

Sanou I., Conte D. and Cardot H. (2019). An Extensible Deep Architecture for Action Recognition Problem. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 191-199. DOI: 10.5220/0007253301910199

in Bibtex Style

@conference{visapp19,
author={Isaac Sanou and Donatello Conte and Hubert Cardot},
title={An Extensible Deep Architecture for Action Recognition Problem},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={191-199},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007253301910199},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - An Extensible Deep Architecture for Action Recognition Problem
SN - 978-989-758-354-4
AU - Sanou I.
AU - Conte D.
AU - Cardot H.
PY - 2019
SP - 191
EP - 199
DO - 10.5220/0007253301910199
PB - SciTePress