Using Action Objects Contextual Information for a Multichannel SVM in an Action Recognition Approach based on Bag of VisualWords

Jordi Bautista-Ballester, Jaume Vergés-Llahí, Domenec Puig

2015

Abstract

Classifying web videos using a Bag of Words (BoW) representation has received increased attention due to its computational simplicity and good performance. The increasing number of categories, including actions with high confusion, and the addition of significant contextual information has lead to most of the authors focusing their efforts on the combination of descriptors. In this field, we propose to use the multikernel Support Vector Machine (SVM) with a contrasted selection of kernels. It is widely accepted that using descriptors that give different kind of information tends to increase the performance. To this end, our approach introduce contextual information, i.e. objects directly related to performed action by pre-selecting a set of points belonging to objects to calculate the codebook. In order to know if a point is part of an object, the objects are previously tracked by matching consecutive frames, and the object bounding box is calculated and labeled. We code the action videos using BoW representation with the object codewords and introduce them to the SVM as an additional kernel. Experiments have been carried out on two action databases, KTH and HMDB, the results provide a significant improvement with respect to other similar approaches.

Paper Citation

in Harvard Style

Bautista-Ballester J., Vergés-Llahí J. and Puig D. (2015). Using Action Objects Contextual Information for a Multichannel SVM in an Action Recognition Approach based on Bag of VisualWords . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 78-86. DOI: 10.5220/0005301000780086

in Bibtex Style

@conference{visapp15,
author={Jordi Bautista-Ballester and Jaume Vergés-Llahí and Domenec Puig},
title={Using Action Objects Contextual Information for a Multichannel SVM in an Action Recognition Approach based on Bag of VisualWords},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={78-86},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005301000780086},
isbn={978-989-758-090-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Using Action Objects Contextual Information for a Multichannel SVM in an Action Recognition Approach based on Bag of VisualWords
SN - 978-989-758-090-1
AU - Bautista-Ballester J.
AU - Vergés-Llahí J.
AU - Puig D.
PY - 2015
SP - 78
EP - 86
DO - 10.5220/0005301000780086