Sciweavers

44 search results - page 3 / 9
» Local minima free Parameterized Appearance Models
Sort
View
MVA
2007
160views Computer Vision» more  MVA 2007»
13 years 7 months ago
Probabilistic Motion Segmentation of Videos for Temporal Super Resolution
A novel scheme is proposed for achieving motion segmentation in low-frame rate videos, with application to temporal super resolution. Probabilistic generative models are commonly ...
Arasanathan Thayananthan, Masahiro Iwasaki, Robert...
NIPS
2007
13 years 7 months ago
Convex Relaxations of Latent Variable Training
We investigate a new, convex relaxation of an expectation-maximization (EM) variant that approximates a standard objective while eliminating local minima. First, a cautionary resu...
Yuhong Guo, Dale Schuurmans
JAIR
2011
114views more  JAIR 2011»
12 years 8 months ago
Properties of Bethe Free Energies and Message Passing in Gaussian Models
We address the problem of computing approximate marginals in Gaussian probabilistic models by using mean field and fractional Bethe approximations. We define the Gaussian fracti...
Botond Cseke, Tom Heskes
IPMI
2007
Springer
14 years 6 months ago
Geometrically Proper Models in Statistical Training
In deformable model segmentation, the geometric training process plays a crucial role in providing shape statistical priors and appearance statistics that are used as likelihoods. ...
Qiong Han, Derek Merck, Josh Levy, Christina Villa...
PAMI
2008
202views more  PAMI 2008»
13 years 5 months ago
Metamorphs: Deformable Shape and Appearance Models
This paper presents a new deformable modeling strategy aimed at integrating shape and appearance in a unified space. If we think traditional deformable models as "active cont...
Xiaolei Huang, Dimitris N. Metaxas