Share Email Print
cover

Proceedings Paper

On the use of MKL for cooking action recognition
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Automatic action recognition in videos is a challenging computer vision task that has become an active research area in recent years. Existing strategies usually use kernel-based learning algorithms that considers a simple combination of different features completely disregarding how such features should be integrated to fit the given problem. Since a given feature is most suitable to describe a given image/video property, the adaptive weighting of such features can improve the performance of the learning algorithm. In this paper, we investigated the use of the Multiple Kernel Learning (MKL) algorithm to adaptive search for the best linear relation among the considered features. MKL is an extension of the support vector machines (SVMs) to work with a weighted linear combination of several single kernels. This approach allows to simultaneously estimate the weights for the multiple kernels combination as well as the underlying SVM parameters. In order to prove the validity of the MKL approach, we considered a descriptor composed of multiple features aligned with dense trajectories. We experimented our approach on a database containing 36 cooking actions. Results confirm that the use of MKL improves the classification performance.

Paper Details

Date Published: 7 March 2014
PDF: 9 pages
Proc. SPIE 9024, Image Processing: Machine Vision Applications VII, 90240G (7 March 2014); doi: 10.1117/12.2041939
Show Author Affiliations
Simone Bianco, Univ. degli Studi di Milano-Bicocca (Italy)
Gianluigi Ciocca, Univ. degli Studi di Milano-Bicocca (Italy)
Paolo Napoletano, Univ. degli Studi di Milano-Bicocca (Italy)


Published in SPIE Proceedings Vol. 9024:
Image Processing: Machine Vision Applications VII
Kurt S. Niel; Philip R. Bingham, Editor(s)

© SPIE. Terms of Use
Back to Top