914 search results - page 107 / 183 » Learning to Segment |
104
Voted
CVPR
2005
IEEE
16 years 2 months ago
2005
IEEE
The goal of motion segmentation and layer extraction can be viewed as the detection and localization of occluding surfaces. A feature that has been shown to be a particularly stro...
87
Voted
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
We propose a novel classification approach for automatically detecting pulmonary embolism (PE) from computedtomography-angiography images. Unlike most existing approaches that req...
113
click to vote
ICPR
2006
IEEE
16 years 1 months ago
2006
IEEE
It is possible to broadly characterize two approaches to probabilistic modeling in terms of generative and discriminative methods. Provided with sufficient training data the discr...
119
Voted
ICPR
2010
IEEE
15 years 6 months ago
2010
IEEE
—We present a meta-learning framework for the design of potential functions for Conditional Random Fields. The design of both node potential and edge potential is formulated as a...
108
Voted
NIPS
2004
15 years 2 months ago
2004
Many machine learning algorithms for clustering or dimensionality reduction take as input a cloud of points in Euclidean space, and construct a graph with the input data points as...