Recognizing Human Actions based on Extreme Learning Machines

Grégoire Lefebvre, Julien Cumin

2016

Abstract

In this paper, we tackle the challenge of action recognition by building robust models from Extreme Learning Machines (ELM). Applying this approach from reduced preprocessed feature vectors on the Microsoft Research Cambridge-12 (MSRC-12) Kinect gesture dataset outperforms the state-of-the-art results with an average correct classification rate of 0.953 over 20 runs, when splitting in two equal subsets for training and testing the 6,244 action instances. This ELM based proposal using a multi-quadric radial basis activation function is compared to other classical classification strategies such as Support Vector Machines (SVM) and Multi-Layer Perceptron (MLP) and advancements are also presented in terms of execution times.

Paper Citation

in Harvard Style

Lefebvre G. and Cumin J. (2016). Recognizing Human Actions based on Extreme Learning Machines . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 478-483. DOI: 10.5220/0005675004780483

in Bibtex Style

@conference{visapp16,
author={Grégoire Lefebvre and Julien Cumin},
title={Recognizing Human Actions based on Extreme Learning Machines},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={478-483},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005675004780483},
isbn={978-989-758-175-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)
TI - Recognizing Human Actions based on Extreme Learning Machines
SN - 978-989-758-175-5
AU - Lefebvre G.
AU - Cumin J.
PY - 2016
SP - 478
EP - 483
DO - 10.5220/0005675004780483