Sciweavers

94 search results - page 2 / 19
» Impact of Dynamic Model Learning on Classification of Human ...
Sort
View
CVPR
2005
IEEE
14 years 7 months ago
Modeling and Learning Contact Dynamics in Human Motion
We propose a simple model of human motion as a switching linear dynamical system where the switches correspond to contact forces with the ground. This significantly improves the m...
Alessandro Bissacco
CVPR
2006
IEEE
14 years 7 months ago
3D People Tracking with Gaussian Process Dynamical Models
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...
Raquel Urtasun, David J. Fleet, Pascal Fua
PAMI
2008
182views more  PAMI 2008»
13 years 4 months ago
Gaussian Process Dynamical Models for Human Motion
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...
Jack M. Wang, David J. Fleet, Aaron Hertzmann
HYBRID
2000
Springer
13 years 8 months ago
A Dynamic Bayesian Network Approach to Tracking Using Learned Switching Dynamic Models
Abstract. Switching linear dynamic systems (SLDS) attempt to describe a complex nonlinear dynamic system with a succession of linear models indexed by a switching variable. Unfortu...
Vladimir Pavlovic, James M. Rehg, Tat-Jen Cham
ICCV
1999
IEEE
14 years 6 months ago
Classification of Human Body Motion
The classification of human body motion is a difficult problem. In particular, the automatic segmentation of sequences containing more than one class of motion is challenging. An ...
Jens Rittscher, Andrew Blake