Title
Learning mixtures of smooth, nonuniform deformation models for probabilistic image matching.
Abstract
By representing images and image prototypes by linear subspacesspanned by \tangent vectors" (derivatives of an image with respectto translation, rotation, etc.), impressive invariance to known typesof uniform distortion can be built into feedforward discriminators.We describe a new probability model that can jointly cluster dataand learn mixtures of nonuniform, smooth deformation elds. Ourelds are based on low-frequency wavelets, so they use very fewparameters to model a wide...
Year
Venue
Keywords
2001
AISTATS
low frequency
Field
DocType
Citations 
Computer vision,Pattern recognition,Computer science,Image matching,Artificial intelligence,Probabilistic logic,Deformation (mechanics),Machine learning
Conference
0
PageRank 
References 
Authors
0.34
2
4
Name
Order
Citations
PageRank
Nebojsa Jojic11397165.68
Brendan J. Frey23637404.51
Patrice Simard31268621.43
David Heckerman469511419.21