Sciweavers

2609 search results - page 455 / 522
» Optimizing for parallelism and data locality
Sort
View
ICCV
1999
IEEE
15 years 9 months ago
Epipolar Geometry Estimation by Tensor Voting in 8D
We present a novel, efficient, initializationfree approach to the problem of epipolar geometry estimation, by formulating it as one of hyperplane inference from a sparse and noisy...
Chi-Keung Tang, Gérard G. Medioni, Mi-Suen ...
SIAMIS
2010
156views more  SIAMIS 2010»
14 years 11 months ago
Learning the Morphological Diversity
This article proposes a new method for image separation into a linear combination of morphological components. Sparsity in fixed dictionaries is used to extract the cartoon and osc...
Gabriel Peyré, Jalal Fadili, Jean-Luc Starc...
JMLR
2006
124views more  JMLR 2006»
15 years 5 months ago
Policy Gradient in Continuous Time
Policy search is a method for approximately solving an optimal control problem by performing a parametric optimization search in a given class of parameterized policies. In order ...
Rémi Munos
BMCBI
2005
89views more  BMCBI 2005»
15 years 4 months ago
An empirical analysis of training protocols for probabilistic gene finders
Background: Generalized hidden Markov models (GHMMs) appear to be approaching acceptance as a de facto standard for state-of-the-art ab initio gene finding, as evidenced by the re...
William H. Majoros, Steven Salzberg
ICCV
2003
IEEE
16 years 6 months ago
Feature Selection for Unsupervised and Supervised Inference: the Emergence of Sparsity in a Weighted-based Approach
The problem of selecting a subset of relevant features in a potentially overwhelming quantity of data is classic and found in many branches of science. Examples in computer vision...
Lior Wolf, Amnon Shashua