Action recognition using ensemble weighted multi-instance learning

Chen, G., Giuliani, M., Clarke, D., Gaschler, A. and Knoll, A. (2014) Action recognition using ensemble weighted multi-instance learning. 2014 IEEE International Conference on Robotics and Automation (ICRA). ISSN 1050-4729 Available from: http://eprints.uwe.ac.uk/31036

Full text not available from this repository

Publisher's URL: http://dx.doi.org/10.1109/ICRA.2014.6907519

Abstract/Description

This paper deals with recognizing human actions in depth video data. Current state-of-the-art action recognition methods use hand-designed features, which are difficult to produce and time-consuming to extend to new modalities. In this paper, we propose a novel, 3.5D representation of a depth video for action recognition. A 3.5D graph of the depth video consists of a set of nodes that are the joints of the human body. Each joint is represented by a set of spatio-temporal features, which are computed by an unsupervised learning approach. However, if occlusions occur, the 3D positions of the joints are noisy which increases the intra-class variations in action classes. To address this problem, we propose the Ensemble Weighted Multi-Instance Learning approach (EnwMi) for the action recognition task. It considers the class imbalance and intra-class variations. We formulate the action recognition task with depth videos as a weighted multi-instance problem. We further integrate an ensemble learning method into the weighted multi-instance learning framework. Our approach is evaluated on Microsoft Research Action3D dataset, and the results show that it outperforms state-of-the-art methods.

Item Type:Article
Uncontrolled Keywords:joints, three-dimensional displays, training, kernel, histograms, feature extraction
Faculty/Department:Faculty of Environment and Technology > Department of Engineering Design and Mathematics
ID Code:31036
Deposited By: Dr M. Giuliani
Deposited On:21 Feb 2017 16:23
Last Modified:21 Feb 2017 16:23

Request a change to this item