Graph-based Kernel Representation of Videos for Traditional Dance Recognition

Christina Chrysouli, Vasileios Gavriilidis, Anastasios Tefas

2014

Abstract

In this paper, we propose a novel graph-based kernel method in order to construct histograms for a bag of words approach, by using similarity measures, applied in activity recognition problems. Bag of words is the most popular framework for performing classification on video data. This framework, however, is an orderless collection of features. We propose a better way to encode action in videos, via altering the histograms. The creation of such histograms is performed based on kernel methods, inspired from graph theory, computed with no great additional computational cost. Moreover, when using the proposed algorithm to construct the histograms, a richer representation of videos is attained. Experiments on folk dances recognition were conducted based on our proposed method, by comparing histograms extracted from a typical bag-of-words framework against histograms of the proposed method, which provided promising results on this challenging task.

Paper Citation

in Harvard Style

Chrysouli C., Gavriilidis V. and Tefas A. (2014). Graph-based Kernel Representation of Videos for Traditional Dance Recognition . In Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2014) ISBN 978-989-758-054-3, pages 195-202. DOI: 10.5220/0005076101950202

in Bibtex Style

@conference{ncta14,
author={Christina Chrysouli and Vasileios Gavriilidis and Anastasios Tefas},
title={Graph-based Kernel Representation of Videos for Traditional Dance Recognition},
booktitle={Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2014)},
year={2014},
pages={195-202},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005076101950202},
isbn={978-989-758-054-3},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2014)
TI - Graph-based Kernel Representation of Videos for Traditional Dance Recognition
SN - 978-989-758-054-3
AU - Chrysouli C.
AU - Gavriilidis V.
AU - Tefas A.
PY - 2014
SP - 195
EP - 202
DO - 10.5220/0005076101950202