Evaluating Method Design Options for Action Classification based on Bags of Visual Words

Victoria Manousaki, Konstantinos Papoutsakis, Antonis Argyros

2018

Abstract

The Bags of Visua lWords (BoVWs) framework has been applied successfully to several computer vision tasks. In this work we are particularly interested on its application to the problem of action recognition/classification. The key design decisions for a method that follows the BoVWs framework are (a) the visual features to be employed, (b) the size of the codebook to be used for representing a certain action and (c) the classifier applied to the developed representation to solve the classification task. We perform several experiments to investigate a variety of options regarding all the aforementioned design parameters. We also propose a new feature type and we suggest a method that determines automatically the size of the codebook. The experimental results show that our proposals produce results that are competitive to the outcomes of state of the art methods.

Download


Paper Citation


in Harvard Style

Manousaki V., Papoutsakis K. and Argyros A. (2018). Evaluating Method Design Options for Action Classification based on Bags of Visual Words. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 185-192. DOI: 10.5220/0006544201850192


in Bibtex Style

@conference{visapp18,
author={Victoria Manousaki and Konstantinos Papoutsakis and Antonis Argyros},
title={Evaluating Method Design Options for Action Classification based on Bags of Visual Words},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={185-192},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006544201850192},
isbn={978-989-758-290-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Evaluating Method Design Options for Action Classification based on Bags of Visual Words
SN - 978-989-758-290-5
AU - Manousaki V.
AU - Papoutsakis K.
AU - Argyros A.
PY - 2018
SP - 185
EP - 192
DO - 10.5220/0006544201850192
PB - SciTePress