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.

Bianco, S., Ciocca, G., Napoletano, P. (2014). On the Use of MKL for Cooking Action Recognition. In Image Processing: Machine Vision Applications VII. SPIE [10.1117/12.2041939].

On the Use of MKL for Cooking Action Recognition

BIANCO, SIMONE;CIOCCA, GIANLUIGI;NAPOLETANO, PAOLO
2014

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
Video analysis, MKL, action recognition
English
Electronic Imaging - Image Processing: Machine Vision Applications VII
2014
Image Processing: Machine Vision Applications VII
2014
9024
90240G
none
Bianco, S., Ciocca, G., Napoletano, P. (2014). On the Use of MKL for Cooking Action Recognition. In Image Processing: Machine Vision Applications VII. SPIE [10.1117/12.2041939].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/50633
Citazioni
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 2
Social impact