The Community for Technology Leaders
Green Image
Issue No. 09 - Sept. (2015 vol. 37)
ISSN: 0162-8828
pp: 1917-1929
Konstantinos Bousmalis , Department of Computing, Imperial College London, London, United Kingdom
Stefanos Zafeiriou , Department of Computing, Imperial College, London
Louis-Philippe Morency , Institute for Creative Technologies, University of Southern California
Maja Pantic , Department of Computing, Imperial College, London
Zoubin Ghahramani , , University of Cambridge, Cambridge, United Kingdom
Hidden conditional random fields (HCRFs) are discriminative latent variable models which have been shown to successfully learn the hidden structure of a given classification problem. An Infinite hidden conditional random field is a hidden conditional random field with a countably infinite number of hidden states, which rids us not only of the necessity to specify a priori a fixed number of hidden states available but also of the problem of overfitting. Markov chain Monte Carlo (MCMC) sampling algorithms are often employed for inference in such models. However, convergence of such algorithms is rather difficult to verify, and as the complexity of the task at hand increases the computational cost of such algorithms often becomes prohibitive. These limitations can be overcome by variational techniques. In this paper, we present a generalized framework for infinite HCRF models, and a novel variational inference approach on a model based on coupled Dirichlet Process Mixtures, the HCRF-DPM. We show that the variational HCRF-DPM is able to converge to a correct number of represented hidden states, and performs as well as the best parametric HCRFs—chosen via cross-validation—for the difficult tasks of recognizing instances of agreement, disagreement, and pain in audiovisual sequences.
Hidden Markov models, Computational modeling, Random variables, Inference algorithms, Joints, Analytical models, Convergence,variational inference, nonparametric models, discriminative models, hidden conditional random fields, dirichlet processes
Konstantinos Bousmalis, Stefanos Zafeiriou, Louis-Philippe Morency, Maja Pantic, Zoubin Ghahramani, "Variational Infinite Hidden Conditional Random Fields", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 37, no. , pp. 1917-1929, Sept. 2015, doi:10.1109/TPAMI.2014.2388228
177 ms
(Ver 3.3 (11022016))