Variational Infinite Hidden Conditional Random Fields
Authors:
- 1 January 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 37 (9) , 1917-1929
Abstract
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.Keywords
Funding Information
- European Research Council (611153)
- Engineering and Physical Sciences Research Council (EP/J017787/1)
This publication has 15 references indexed in Scilit:
- Infinite Hidden Conditional Random Fields for Human Behavior AnalysisIEEE Transactions on Neural Networks and Learning Systems, 2012
- Modeling hidden dynamics of multimodal cues for spontaneous agreement and disagreement recognition2011
- The Infinite Hidden Markov Random Field ModelIEEE Transactions on Neural Networks, 2010
- An HDP-HMM for systems with state persistence2008
- Hidden Conditional Random FieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Nonparametric Bayesian Image SegmentationInternational Journal of Computer Vision, 2007
- Latent-Dynamic Discriminative Models for Continuous Gesture Recognition2007
- Hierarchical Dirichlet ProcessesJournal of the American Statistical Association, 2006
- Variational inference for Dirichlet process mixturesBayesian Analysis, 2006
- On the Goldstein-Levitin-Polyak gradient projection methodIEEE Transactions on Automatic Control, 1976