CVPR
2011
IEEE
13 years 5 months ago
2011
IEEE
We propose a novel nonlinear, probabilistic and variational method for adding shape information to level setbased segmentation and tracking. Unlike previous work, we represent sha...
JMLR
2010
13 years 8 months ago
2010
Existing approaches to multi-view learning are particularly effective when the views are either independent (i.e, multi-kernel approaches) or fully dependent (i.e., shared latent ...
ACCV
2010
Springer
13 years 8 months ago
2010
Springer
Discriminative approaches for human pose estimation model the functional mapping, or conditional distribution, between image features and 3D pose. Learning such multi-modal models ...
NECO
1998
14 years 1 months ago
1998
Latent variable models represent the probability density of data in a space of several dimensions in terms of a smaller number of latent, or hidden, variables. A familiar example ...
PAMI
2008
14 years 1 months ago
2008
We introduce Gaussian process dynamical models (GPDMs) for nonlinear time series analysis, with applications to learning models of human pose and motion from high-dimensional motio...
CIKM
2009
Springer
14 years 6 months ago
2009
Springer
Traditional ranking mainly focuses on one type of data source, and effective modeling still relies on a sufficiently large number of labeled or supervised examples. However, in m...
MM
2004
ACM
14 years 7 months ago
2004
ACM
We address the problem of unsupervised image auto-annotation with probabilistic latent space models. Unlike most previous works, which build latent space representations assuming ...
MM
2005
ACM
14 years 7 months ago
2005
ACM
Latent Semantic Analysis (LSA) has shown encouraging performance for the problem of unsupervised image automatic annotation. LSA conducts annotation by keywords propagation on a l...
MLMI
2007
Springer
14 years 7 months ago
2007
Springer
We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) [1]...
HUMO
2007
Springer
14 years 8 months ago
2007
Springer
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...