Sciweavers

480 search results - page 69 / 96
» Parameterized Modeling and Recognition of Activities
Sort
View
ICANN
2009
Springer
15 years 2 months ago
Switching Hidden Markov Models for Learning of Motion Patterns in Videos
Abstract. Building on the current understanding of neural architecture of the visual cortex, we present a graphical model for learning and classification of motion patterns in vid...
Matthias Höffken, Daniel Oberhoff, Marina Kol...
PAMI
2008
202views more  PAMI 2008»
14 years 9 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
AAAI
2010
14 years 11 months ago
G-Optimal Design with Laplacian Regularization
In many real world applications, labeled data are usually expensive to get, while there may be a large amount of unlabeled data. To reduce the labeling cost, active learning attem...
Chun Chen, Zhengguang Chen, Jiajun Bu, Can Wang, L...
CVIU
2006
176views more  CVIU 2006»
14 years 9 months ago
Temporal motion models for monocular and multiview 3D human body tracking
We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable ...
Raquel Urtasun, David J. Fleet, Pascal Fua
CORR
2012
Springer
198views Education» more  CORR 2012»
13 years 5 months ago
Lipschitz Parametrization of Probabilistic Graphical Models
We show that the log-likelihood of several probabilistic graphical models is Lipschitz continuous with respect to the ￿p-norm of the parameters. We discuss several implications ...
Jean Honorio