Sciweavers

64 search results - page 9 / 13
» Multifactor Gaussian process models for style-content separa...
Sort
View
ICML
2008
IEEE
14 years 8 months ago
Topologically-constrained latent variable models
In dimensionality reduction approaches, the data are typically embedded in a Euclidean latent space. However for some data sets this is inappropriate. For example, in human motion...
Raquel Urtasun, David J. Fleet, Andreas Geiger, Jo...
ICCV
2007
IEEE
15 years 2 months ago
 A Component Based Deformable Model for Generalized Face Alignment
This paper presents a component based deformable model for generalized face alignment, in which a novel bistage statistical framework is proposed to account for both local and g...
Yuchi Huang, Qingshan Liu, Dimitris Metaxas
ICPR
2000
IEEE
14 years 8 months ago
Mixture Densities for Video Objects Recognition
The appearance of non-rigid objects detected and tracked in video streams is highly variable and therefore makes the identification of similar objects very complex. Furthermore, i...
Riad I. Hammoud, Roger Mohr
ICA
2007
Springer
13 years 11 months ago
Conjugate Gamma Markov Random Fields for Modelling Nonstationary Sources
In modelling nonstationary sources, one possible strategy is to define a latent process of strictly positive variables to model variations in second order statistics of the underly...
Ali Taylan Cemgil, Onur Dikmen
JMM2
2007
148views more  JMM2 2007»
13 years 7 months ago
Object Segmentation Using Background Modelling and Cascaded Change Detection
— The automatic extraction and analysis of visual information is becoming generalised. The first step in this processing chain is usually separating or segmenting the captured v...
Luís Filipe Teixeira, Jaime S. Cardoso, Lu&...