Issue No. 10 - October (2007 vol. 29)
We present a discriminative latent variable model for classification problems in structured domains where inputs can be represented by a graph of local observations. A hidden-state Conditional Random Field framework learns a set of latent variables conditioned on local features. Observations need not be independent and may overlap in space and time.
object recognition, model, supervised learning, classification
A. Quattoni, L. Morency, T. Darrell, M. Collins and S. Wang, "Hidden Conditional Random Fields," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 29, no. , pp. 1848-1852, 2007.