9 search results - page 1 / 2 » Models of Co-occurrence |
WACV
2005
IEEE
15 years 3 months ago
2005
IEEE
A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...
103
click to vote
LREC
2010
14 years 11 months ago
2010
This paper presents a comparison of three computational approaches to selectional preferences: (i) an intuitive distributional approach that uses second-order co-occurrence of pre...
TKDE
2008
14 years 9 months ago
2008
135
click to vote
Publication
Gibbs random eld model with multiple pairwise pixel interactions describes each type of spatially homogeneous image textures in terms of a pixel neighbourhood and Gibbs potentials...
LREC
2008
14 years 11 months ago
2008
Distributional, corpus-based descriptions have frequently been applied to model aspects of word meaning. However, distributional models that use corpus data as their basis have on...