Name
Abstract | ||
|---|---|---|
Hidden Markov Models (HMMs) are very popular generative models for sequence data. Recent research has, however, shown that Conditional Random Fields (CRFs), a type of discriminative model, outperform HMMs in many tasks. We have previously proposed Hierarchical Hidden Conditional Random Fields (HHCRFs), a discriminative model corresponding to hierarchical HMMs (HHMMs). Given observations, HHCRFs model the conditional probability of the states at the upper levels. States at the lower levels are hidden and marginalized in the model definition. In addition, we have developed a parameter learning algorithm that requires only the states at the upper levels in the training data. Previously we applied HHCRFs to the segmentation of electroen-cephalographic (EEG) data for a Brain-Computer Interface, and showed that HHCRFs outperform HHMMs. In this paper, we apply HHCRFs to labeling artificial data and sports video segmentation. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1007/978-3-642-02490-0_87 | ICONIP (1) |
Keywords | Field | DocType |
hierarchical hidden crf,discriminative model,training data,hhcrfs model,artificial data,upper level,outperform hmms,hierarchical hmms,popular generative model,sports video segmentation,sequence data,model definition,conditional random field,brain computer interface,conditional probability,hidden markov model | Conditional probability distribution,Maximum-entropy Markov model,Computer science,Artificial intelligence,Discriminative model,Conditional random field,Pattern recognition,Conditional probability,Speech recognition,Hidden Markov model,Machine learning,Dynamic Bayesian network,Generative model | Conference |
Volume | ISSN | ISBN |
5506 | 0302-9743 | 3-642-02489-0 |
Citations | PageRank | References |
1 | 0.37 | 15 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hirotaka Tamada | 1 | 1 | 0.37 |
| Akira Hayashi | 2 | 51 | 9.08 |