Dynamical binary latent variable models for 3D human pose tracking

Computer Vision and Pattern Recognition, 2010, Pages 631-638.

Cited by: 141|Bibtex|Views17|Links
EI WOS
Keywords:
Boltzmann machinesfiltering theoryimage motion analysispose estimationprobabilityMore(8+)

Abstract:

We introduce a new class of probabilistic latent vari- able model called the Implicit Mixture of Conditional Re- stricted Boltzmann Machines (imCRBM) for use in human pose tracking. Key properties of the imCRBM are as fol- lows: (1) learning is linear in the number of training exem- plars so it can be learned from large datasets; (2) it l...More

Code:

Data:

Your rating :
0

 

Tags
Comments