Sciweavers

1086 search results - page 16 / 218
» Knowledge-based part correspondence
Sort
View
EMNLP
2006
13 years 10 months ago
Domain Adaptation with Structural Correspondence Learning
Discriminative learning methods are widely used in natural language processing. These methods work best when their training and test data are drawn from the same distribution. For...
John Blitzer, Ryan T. McDonald, Fernando Pereira
IJCV
2006
116views more  IJCV 2006»
13 years 8 months ago
Contextual Inference in Contour-Based Stereo Correspondence
Standard approaches to stereo correspondence have difficulty when scene structure does not lie in or near the frontal parallel plane, in part because an orientation disparity as we...
Gang Li, Steven W. Zucker
ECCV
2010
Springer
12 years 2 months ago
Voting by Grouping Dependent Parts
Hough voting methods efficiently handle the high complexity of multiscale, category-level object detection in cluttered scenes. The primary weakness of this approach is however t...
Pradeep Yarlagadda, Antonio Monroy and Bjorn Ommer
CORR
2011
Springer
160views Education» more  CORR 2011»
13 years 3 months ago
When is social computation better than the sum of its parts?
good solutions to complex problems. In many examples, individuals trying to solve superior global solution. This suggests that there may be general principles of information aggre...
Vadas Gintautas, Aric A. Hagberg, Luís M. A...
MOC
2002
75views more  MOC 2002»
13 years 8 months ago
Average equidistribution and statistical independence properties of digital inversive pseudorandom numbers over parts of the per
This article deals with the digital inversive method for generating uniform pseudorandom numbers. Equidistribution and statistical independence properties of the generated pseudora...
Frank Emmerich