Sciweavers

1476 search results - page 168 / 296
» Robust constraint-consistent learning
Sort
View
ICML
2009
IEEE
16 years 7 months ago
On primal and dual sparsity of Markov networks
Sparsity is a desirable property in high dimensional learning. The 1-norm regularization can lead to primal sparsity, while max-margin methods achieve dual sparsity. Combining the...
Jun Zhu, Eric P. Xing
CIG
2005
IEEE
15 years 12 months ago
A Generic Approach for Generating Interesting Interactive Pac-Man Opponents
This paper follows on from our previous work focused on formulating an efficient generic measure of user’s satisfaction (‘interest’) when playing predator/prey games. Viewin...
Georgios N. Yannakakis, John Hallam
ICCV
2005
IEEE
15 years 12 months ago
On the Spatial Statistics of Optical Flow
We develop a method for learning the spatial statistics of optical flow fields from a novel training database. Training flow fields are constructed using range images of natur...
Stefan Roth, Michael J. Black
ECCV
2010
Springer
15 years 11 months ago
Stacked Hierarchical Labeling
In this work we propose a hierarchical approach for labeling semantic objects and regions in scenes. Our approach is reminiscent of early vision literature in that we use a decompo...
CVPR
2010
IEEE
15 years 11 months ago
Anatomical Parts-Based Regression Using Non-Negative Matrix Factorization
Non-negative matrix factorization (NMF) is an excellent tool for unsupervised parts-based learning, but proves to be ineffective when parts of a whole follow a specific pattern. ...
Swapna Joshi, Karthikeyan Shanmugavadivel, B.S. Ma...