274 search results - page 14 / 55 » Activity Recognition from Sparsely Labeled Data Using Multi-... |
ECCV
2010
Springer
13 years 12 months ago
2010
Springer
Abstract. In this paper we investigate the problem of exploiting multiple sources of information for object recognition tasks when additional modalities that are not present in the...
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
Current hidden Markov acoustic modeling for large vocabulary continuous speech recognition (LVCSR) relies on the availability of abundant labeled transcriptions. Given that speech...
KDD
2010
ACM
13 years 9 months ago
2010
ACM
In plenty of scenarios, data can be represented as vectors mathematically abstracted as points in a Euclidean space. Because a great number of machine learning and data mining app...
NLE
2008
13 years 7 months ago
2008
For complex tasks such as parse selection, the creation of labelled training sets can be extremely costly. Resource-efficient schemes for creating informative labelled material mu...
ICDM
2006
IEEE
14 years 1 months ago
2006
IEEE
In active learning, a machine learning algorithm is given an unlabeled set of examples U, and is allowed to request labels for a relatively small subset of U to use for training. ...