Hidden Conditional Random Fields

Author

Quattoni, Ariadna ; Wang, Sybor ; Morency, Louis-Philippe ; Collins, Michael ; Darrell, Trevor

Author_Institution

Massachusetts Inst. of Technol., Cambridge

Volume

29

Issue

10

fYear

2007

Firstpage

1848

Lastpage

1852

Abstract

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.

Keywords

graph theory; learning (artificial intelligence); discriminative latent variable model; hidden-state conditional random field framework; supervised learning; Bayesian methods; Graphical models; Handicapped aids; Hidden Markov models; Inference algorithms; Labeling; Natural language processing; Object recognition; Parameter estimation; Supervised learning; classification; model; object recognition; supervised learning; Algorithms; Artificial Intelligence; Computer Simulation; Data Interpretation, Statistical; Image Enhancement; Image Interpretation, Computer-Assisted; Markov Chains; Models, Statistical; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/TPAMI.2007.1124

Filename

4293212