Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6959323 | Signal Processing | 2015 | 15 Pages |
Abstract
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.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Signal Processing
Authors
Guang Chen, Daniel Clarke, Manuel Giuliani, Andre Gaschler, Alois Knoll,