Sciweavers

1956 search results - page 82 / 392
» Learning the Relative Importance of Features in Image Data
Sort
View
TKDE
2010
137views more  TKDE 2010»
13 years 7 months ago
A Survey on Transfer Learning
—A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. How...
Sinno Jialin Pan, Qiang Yang
EMNLP
2009
13 years 6 months ago
Reverse Engineering of Tree Kernel Feature Spaces
We present a framework to extract the most important features (tree fragments) from a Tree Kernel (TK) space according to their importance in the target kernelbased machine, e.g. ...
Daniele Pighin, Alessandro Moschitti
ICPR
2010
IEEE
14 years 3 months ago
Object Recognition and Localization Via Spatial Instance Embedding
—We propose an approach for improving object recognition and localization using spatial kernels together with instance embedding. Our approach treats each image as a bag of insta...
Nazli Ikizler Cinbis, Stan Sclaroff
CVPR
2012
IEEE
11 years 11 months ago
Weakly supervised structured output learning for semantic segmentation
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...
Alexander Vezhnevets, Vittorio Ferrari, Joachim M....
DAGM
2006
Springer
14 years 12 days ago
Robust MEG Source Localization of Event Related Potentials: Identifying Relevant Sources by Non-Gaussianity
Independent Component Analysis (ICA) is a frequently used preprocessing step in source localization of MEG and EEG data. By decomposing the measured data into maximally independent...
Peter Breun, Moritz Grosse-Wentrup, Wolfgang Utsch...