Sciweavers

1717 search results - page 223 / 344
» A Computable Spectral Theorem
Sort
View
CVPR
2012
IEEE
13 years 8 months ago
Multi-class cosegmentation
Bottom-up, fully unsupervised segmentation remains a daunting challenge for computer vision. In the cosegmentation context, on the other hand, the availability of multiple images ...
Armand Joulin, Francis Bach, Jean Ponce
ERSHOV
2009
Springer
15 years 9 months ago
Anti-unification Algorithms and Their Applications in Program Analysis
A term t is called a template of terms t1 and t2 iff t1 = t1 and t2 = t2, for some substitutions 1 and 2. A template t of t1 and t2 is called the most specific iff for any template...
Peter E. Bulychev, Egor V. Kostylev, Vladimir A. Z...
CORR
2010
Springer
116views Education» more  CORR 2010»
15 years 5 months ago
Where are the hard manipulation problems?
One possible escape from the Gibbard-Satterthwaite theorem is computational complexity. For example, it is NP-hard to compute if the STV rule can be manipulated. However, there is...
Toby Walsh
CVPR
2009
IEEE
1133views Computer Vision» more  CVPR 2009»
17 years 19 days ago
Sparse Subspace Clustering
We propose a method based on sparse representation (SR) to cluster data drawn from multiple low-dimensional linear or affine subspaces embedded in a high-dimensional space. Our ...
Ehsan Elhamifar, René Vidal
CVPR
2009
IEEE
17 years 19 days ago
Shared Kernel Information Embedding for Discriminative Inference
Latent Variable Models (LVM), like the Shared-GPLVM and the Spectral Latent Variable Model, help mitigate over- fitting when learning discriminative methods from small or modera...
David J. Fleet, Leonid Sigal, Roland Memisevic