38 search results - page 1 / 8 » Multi-View Learning over Structured and Non-Identical Output... |
89
Voted
UAI
2008
15 years 9 days ago
2008
In many machine learning problems, labeled training data is limited but unlabeled data is ample. Some of these problems have instances that can be factored into multiple views, ea...
101
Voted
JMLR
2012
13 years 1 months ago
2012
Often when modeling structured domains, it is desirable to leverage information that is not naturally expressed as simply a label. Examples include knowledge about the evaluation ...
147
Voted
CVPR
2012
IEEE
13 years 1 months ago
2012
IEEE
We address the problem of weakly supervised semantic segmentation. The training images are labeled only by the classes they contain, not by their location in the image. On test im...
ICML
2008
IEEE
15 years 11 months ago
2008
IEEE
Tsochantaridis et al. (2005) proposed two formulations for maximum margin training of structured spaces: margin scaling and slack scaling. While margin scaling has been extensivel...
ECCV
2008
Springer
16 years 23 days ago
2008
Springer
Sliding window classifiers are among the most successful and widely applied techniques for object localization. However, training is typically done in a way that is not specific to...