Sciweavers

1345 search results - page 143 / 269
» Efficient Learning of Relational Object Class Models
Sort
View
114
Voted
IJCV
2000
97views more  IJCV 2000»
15 years 3 months ago
Contour Tracking in Clutter: A Subset Approach
A new method for tracking contours of moving objects in clutter is presented. For a given object, a model of its contours is learned from training data in the form of a subset of c...
Daniel Freedman, Michael S. Brandstein
CVPR
2005
IEEE
16 years 5 months ago
A Direct Method for Modeling Non-Rigid Motion with Thin Plate Spline
Thin plate spline (TPS) transformations have been applied to non-rigid shape matching with impressive results. However, existing methods often use a sparse set of point correspond...
Jongwoo Lim, Ming-Hsuan Yang
ACL
2009
15 years 1 months ago
Better Word Alignments with Supervised ITG Models
This work investigates supervised word alignment methods that exploit inversion transduction grammar (ITG) constraints. We consider maximum margin and conditional likelihood objec...
Aria Haghighi, John Blitzer, John DeNero, Dan Klei...
146
Voted
CVPR
2009
IEEE
1390views Computer Vision» more  CVPR 2009»
16 years 10 months ago
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
In this paper we present a method for learning classspecific features for recognition. Recently a greedy layerwise procedure was proposed to initialize weights of deep belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
ICML
2010
IEEE
15 years 4 months ago
Learning Markov Logic Networks Using Structural Motifs
Markov logic networks (MLNs) use firstorder formulas to define features of Markov networks. Current MLN structure learners can only learn short clauses (4-5 literals) due to extre...
Stanley Kok, Pedro Domingos