190 search results - page 29 / 38 » Exploiting multiple classifier types with active learning |
EUROCOLT
1997
Springer
13 years 11 months ago
1997
Springer
Most of the work on the Vapnik-Chervonenkis dimension of neural networks has been focused on feedforward networks. However, recurrent networks are also widely used in learning app...
ICPR
2008
IEEE
14 years 8 months ago
2008
IEEE
This paper investigates several issues in the problem of detecting handwritten markings, or annotations, on printed documents. One issue is to define the appropriate units over wh...
CVPR
2010
IEEE
14 years 2 months ago
2010
IEEE
We address the character identification problem in
movies and television videos: assigning names to faces on
the screen. Most prior work on person recognition in video
assumes s...
UAI
2004
13 years 8 months ago
2004
This paper uses Factored Latent Analysis (FLA) to learn a factorized, segmental representation for observations of tracked objects over time. Factored Latent Analysis is latent cl...
CVPR
2005
IEEE
14 years 8 months ago
2005
IEEE
We introduce a behavior-based similarity measure which tells us whether two different space-time intensity patterns of two different video segments could have resulted from a simi...