3716 search results - page 545 / 744 » On the monotonization of the training set |
334
click to vote
DAGM
2011
Springer
14 years 6 months ago
2011
Springer
The supervised learning paradigm assumes in general that both training and test data are sampled from the same distribution. When this assumption is violated, we are in the setting...
211
click to vote
PAMI
2012
13 years 9 months ago
2012
— Context is critical for reducing the uncertainty in object detection. However, context modelling is challenging because there are often many different types of contextual infor...
178
click to vote
ICCV
2007
IEEE
16 years 8 months ago
2007
IEEE
Unsupervised categorization of images or image parts is often needed for image and video summarization or as a preprocessing step in supervised methods for classification, trackin...
200
click to vote
ICCV
2005
IEEE
16 years 8 months ago
2005
IEEE
We present an efficient method for learning part-based object class models from unsegmented images represented as sets of salient features. A model includes parts' appearance...
187
click to vote
KDD
2009
ACM
16 years 7 months ago
2009
ACM
We present a new approach to large-scale graph mining based on so-called backbone refinement classes. The method efficiently mines tree-shaped subgraph descriptors under minimum f...