1575 search results - page 3 / 315 » Unsupervised Learning of Models for Recognition |
PAMI
2012
11 years 10 months ago
2012
Which one comes first: segmentation or recognition? We propose a unified framework for carrying out the two simultaneously and without supervision. The framework combines a fle...
ICASSP
2008
IEEE
14 years 1 months ago
2008
IEEE
Non-negative matrix factorisation (NMF) is an unsupervised learning technique that decomposes a non-negative data matrix into a product of two lower rank non-negative matrices. Th...
ACCV
2009
Springer
14 years 2 months ago
2009
Springer
The method based on local features has an advantage that the important local motion feature is represented as bag-of-features, but lacks the location information. Additionally, in ...
NAACL
2003
13 years 8 months ago
2003
This paper describes an application of active learning methods to the classification of phone strings recognized using unsupervised phonotactic models. The only training data req...
ICML
2009
IEEE
14 years 8 months ago
2009
IEEE
We describe an adaptation and application of a search-based structured prediction algorithm "Searn" to unsupervised learning problems. We show that it is possible to red...