216 search results - page 12 / 44 » Multiple kernel learning from sets of partially matching ima... |
CVPR
2006
IEEE
15 years 11 months ago
2006
IEEE
Segmentation involves separating an object from the background. In this work, we propose a novel segmentation method combining image information with prior shape knowledge, within...
ICML
2007
IEEE
15 years 10 months ago
2007
IEEE
We present a new machine learning framework called "self-taught learning" for using unlabeled data in supervised classification tasks. We do not assume that the unlabele...
100
click to vote
ECAI
2010
Springer
14 years 7 months ago
2010
Springer
The proposed feature selection method aims to find a minimum subset of the most informative variables for classification/regression by efficiently approximating the Markov Blanket ...
106
Voted
DAGSTUHL
2006
14 years 11 months ago
2006
One of the bottlenecks of current recognition (and graph matching) systems is their assumption of one-to-one feature (node) correspondence. This assumption breaks down in the gener...
81
Voted
CVPR
2004
IEEE
15 years 11 months ago
2004
IEEE
Retrieving images in response to textual queries requires some knowledge of the semantics of the picture. Here, we show how we can do both automatic image annotation and retrieval...