Paper Info
Title
Combining unsupervised learning and discrimination for 3D action recognition.
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. HighlightsWe deal with recognizing 3D human actions by combining two ideas: unsupervised feature learning and discriminative feature mining.We are the first work to use unsupervised learning to represent 3D depth video data.We propose an ensemble approach with a discriminative multi-kernel learning algorithm to model 3D human actions.
Year
DOI
Venue
2015
10.1016/j.sigpro.2014.08.024
Signal Processing
Keywords
Field
DocType
ensemble learning,unsupervised learning
Competitive learning,Semi-supervised learning,Pattern recognition,Computer science,Feature extraction,Unsupervised learning,Feature (machine learning),Artificial intelligence,Discriminative model,Ensemble learning,Feature learning,Machine learning
Journal
Volume
Issue
ISSN
110
C
0165-1684
Citations 
PageRank 
References 
14
0.64
45
Authors
5
Name
Order
Citations
PageRank
Guang Chen1375.15
Daniel Clarke2171.37
Manuel Giuliani323820.89
Andre Gaschler41359.32
Alois Knoll Knoll51700271.32