Sciweavers

371 search results - page 44 / 75
» Probabilistic Hierarchical Face Model for Feature Localizati...
Sort
View
ICASSP
2008
IEEE
14 years 3 months ago
Sparse and shift-invariant feature extraction from non-negative data
In this paper we describe a technique that allows the extraction of multiple local shift-invariant features from analysis of non-negative data of arbitrary dimensionality. Our app...
Paris Smaragdis, Bhiksha Raj, Madhusudana V. S. Sh...
CVPR
2006
IEEE
14 years 11 months ago
Training Deformable Models for Localization
We present a new method for training deformable models. Assume that we have training images where part locations have been labeled. Typically, one fits a model by maximizing the l...
Deva Ramanan, Cristian Sminchisescu
ICDM
2007
IEEE
289views Data Mining» more  ICDM 2007»
14 years 3 months ago
Latent Dirichlet Conditional Naive-Bayes Models
In spite of the popularity of probabilistic mixture models for latent structure discovery from data, mixture models do not have a natural mechanism for handling sparsity, where ea...
Arindam Banerjee, Hanhuai Shan
CVPR
2009
IEEE
15 years 4 months ago
Dense 3D Motion Capture for Human Faces
This paper proposes a novel approach to motion capture from multiple, synchronized video streams, specifically aimed at recording dense and accurate models of the structure and ...
Yasutaka Furukawa (University of Washington), Jean...
WSCG
2003
164views more  WSCG 2003»
13 years 10 months ago
Refinement and Hierarchical Coarsening Schemes for Triangulated Surfaces
We present a refinement and a coarsening (also simplification or decimation) algorithm for the adaptive representation of bivariate functions. The algorithms have proved to be eff...
José P. Suárez, Angel Plaza