Combining unsupervised learning and discrimination for 3D action recognition

Chen, G., Clarke, D., Giuliani, M., Gaschler, A. and Knoll, A. (2015) Combining unsupervised learning and discrimination for 3D action recognition. Signal Processing, 110. pp. 67-81. ISSN 0165-1684 Available from: http://eprints.uwe.ac.uk/31011

Full text not available from this repository

Publisher's URL: http://dx.doi.org/10.1016/j.sigpro.2014.08.024

Abstract/Description

Previous work on 3D action recognition has focused on using hand-designed features, either from depth videos or 2D videos. In this work, we present an effective way to combine unsupervised feature learning with discriminative feature mining. Unsupervised feature learning allows us to extract spatio-temporal features from unlabeled video data. With this, we can avoid the cumbersome process of designing feature extraction by hand. We propose an ensemble approach using a discriminative learning algorithm, where each base learner is a discriminative multi-kernel-learning classifier, trained to learn an optimal combination of joint-based features. Our evaluation includes a comparison to state-of-the-art methods on the MSRAction 3D dataset, where our method, abbreviated EnMkl, outperforms earlier methods. Furthermore, we analyze the efficiency of our approach in a 3D action recognition system.

Item Type:Article
Uncontrolled Keywords:human action recognition, depth camera, unsupervised learning, multi-kernel learning, ensemble learning
Faculty/Department:Faculty of Environment and Technology > Department of Engineering Design and Mathematics
ID Code:31011
Deposited By: Dr M. Giuliani
Deposited On:20 Feb 2017 14:29
Last Modified:20 Feb 2017 14:29

Request a change to this item