The hidden-unit conditional random field (CRF) is a model for structured prediction that is more powerful than standard linear CRFs. The additional modeling power of hidden-unit CRFs stems from its binary stochastic hidden units that model latent data structure that is relevant to classification. The hidden units are conditionally independent given the data and the labels, as a result of which they can be marginalized out efficiently during inference.
The code implements various training algorithms for hidden-unit CRFs, as well as for traditional linear-chain CRFs.
The model can be used for SSPNet-related time series prediction tasks such as action unit classification, speech recognition, and gesture recognition.
The model is described in detail in the following paper:
- L.J.P. van der Maaten, M. Welling, and L.K. Saul. Hidden-Unit Conditional Random Fields. To appear in Proceedings of the International Conference on Artificial Intelligence & Statistics (AI-STATS), 2011
- year: 2011
- month: Mar
- url: http://cseweb.ucsd.edu/~lvdmaaten/hucrf
- main_author: Laurens van der Maaten
- license: Only for non-commercial purposes
- platform: Matlab (all platforms)