Sciweavers

2168 search results - page 310 / 434
» Using Approximation Hardness to Achieve Dependable Computati...
Sort
View
CVPR
2003
IEEE
16 years 6 months ago
An Efficient Approach to Learning Inhomogeneous Gibbs Model
Inhomogeneous Gibbs model (IGM) [4] is an effective maximum entropy model in characterizing complex highdimensional distributions. However, its training process is so slow that th...
Ziqiang Liu, Hong Chen, Heung-Yeung Shum
ECCV
2004
Springer
16 years 5 months ago
A Feature-Based Approach for Determining Dense Long Range Correspondences
Planar motion models can provide gross motion estimation and good segmentation for image pairs with large inter-frame disparity. However, as the disparity becomes larger, the resul...
Josh Wills, Serge Belongie
ICPR
2002
IEEE
16 years 5 months ago
Bayesian Networks as Ensemble of Classifiers
Classification of real-world data poses a number of challenging problems. Mismatch between classifier models and true data distributions on one hand and the use of approximate inf...
Ashutosh Garg, Vladimir Pavlovic, Thomas S. Huang
HPCA
2007
IEEE
16 years 4 months ago
Exploiting Postdominance for Speculative Parallelization
Task-selection policies are critical to the performance of any architecture that uses speculation to extract parallel tasks from a sequential thread. This paper demonstrates that ...
Mayank Agarwal, Kshitiz Malik, Kevin M. Woley, Sam...
DCC
2005
IEEE
16 years 3 months ago
Towards Practical Minimum-Entropy Universal Decoding
Minimum-entropy decoding is a universal decoding algorithm used in decoding block compression of discrete memoryless sources as well as block transmission of information across di...
Todd P. Coleman, Muriel Médard, Michelle Ef...