Human Action Recognition using Multi-Kernel Learning for Temporal Residual Network

Saima Nazir, Yu Qian, Muhammad Haroon Yousaf, Sergio A. Velastin, Ebroul Izquierdo, Eduard Vazquez

2019

Abstract

Deep learning has led to a series of breakthrough in the human action recognition field. Given the powerful representational ability of residual networks (ResNet), performance in many computer vision tasks including human action recognition has improved. Motivated by the success of ResNet, we use the residual network and its variations to obtain feature representation. Bearing in mind the importance of appearance and motion information for action representation, our network utilizes both for feature extraction. Appearance and motion features are further fused for action classification using a multi-kernel support vector machine (SVM). We also investigate the fusion of dense trajectories with the proposed network to boost up the network performance. We evaluate our proposed methods on a benchmark dataset (HMDB-51) and results shows the multi-kernel learning shows the better performance than the fusion of classification score from deep network SoftMax layer. Our proposed method also shows good performance as compared to the recent state-of-the-art methods.

Paper Citation

in Harvard Style

Nazir S., Qian Y., Yousaf M., Velastin S., Izquierdo E. and Vazquez E. (2019). Human Action Recognition using Multi-Kernel Learning for Temporal Residual Network. 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 420-426. DOI: 10.5220/0007371104200426

in Bibtex Style

@conference{visapp19,
author={Saima Nazir and Yu Qian and Muhammad Haroon Yousaf and Sergio A. Velastin and Ebroul Izquierdo and Eduard Vazquez},
title={Human Action Recognition using Multi-Kernel Learning for Temporal Residual Network},
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={420-426},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007371104200426},
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 - Human Action Recognition using Multi-Kernel Learning for Temporal Residual Network
SN - 978-989-758-354-4
AU - Nazir S.
AU - Qian Y.
AU - Yousaf M.
AU - Velastin S.
AU - Izquierdo E.
AU - Vazquez E.
PY - 2019
SP - 420
EP - 426
DO - 10.5220/0007371104200426
PB - SciTePress