319 search results - page 28 / 64 » Two-view feature generation model for semi-supervised learni... |
ECCV
2008
Springer
14 years 9 months ago
2008
Springer
Abstract. We present a comparative study on how to use discriminative learning methods such as classification, regression, and ranking to address deformable shape segmentation. Tra...
ICPR
2008
IEEE
14 years 8 months ago
2008
IEEE
In this paper, we propose a generative model-based approach for audio-visual event classification. This approach is based on a new unsupervised learning method using an extended p...
ACAL
2009
Springer
13 years 11 months ago
2009
Springer
Abstract. We explore a new definition of creativity -- one which emphasizes the statistical capacity of a system to generate previously unseen patterns -- and discuss motivations f...
NIPS
2007
13 years 8 months ago
2007
We show how to use unlabeled data and a deep belief net (DBN) to learn a good covariance kernel for a Gaussian process. We first learn a deep generative model of the unlabeled da...
ACL
2008
13 years 9 months ago
2008
We present a method for learning bilingual translation lexicons from monolingual corpora. Word types in each language are characterized by purely monolingual features, such as con...