University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Data mining for action recognition

Gilbert, A and Bowden, R (2015) Data mining for action recognition Computer Vision -- ACCV 2014, 9007. pp. 290-303.

[img]
Preview
Text (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview
[img]
Preview
Text
Gilbert_ACCV_2014pp.pdf
Available under License : See the attached licence file.

Download (4MB) | Preview

Abstract

© Springer International Publishing Switzerland 2015. In recent years, dense trajectories have shown to be an efficient representation for action recognition and have achieved state-of-the art results on a variety of increasingly difficult datasets. However, while the features have greatly improved the recognition scores, the training process and machine learning used hasn’t in general deviated from the object recognition based SVM approach. This is despite the increase in quantity and complexity of the features used. This paper improves the performance of action recognition through two data mining techniques, APriori association rule mining and Contrast Set Mining. These techniques are ideally suited to action recognition and in particular, dense trajectory features as they can utilise the large amounts of data, to identify far shorter discriminative subsets of features called rules. Experimental results on one of the most challenging datasets, Hollywood2 outperforms the current state-of-the-art.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
AuthorsEmailORCID
Gilbert, AUNSPECIFIEDUNSPECIFIED
Bowden, RUNSPECIFIEDUNSPECIFIED
Date : 17 April 2015
Identification Number : 10.1007/978-3-319-16814-2_19
Additional Information : © Springer International Publishing Switzerland 2015. The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-16814-2_19
Depositing User : Symplectic Elements
Date Deposited : 21 Oct 2015 09:03
Last Modified : 17 Apr 2016 01:08
URI: http://epubs.surrey.ac.uk/id/eprint/808935

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800