Dynamical Binary Latent Variable Models for 3D Human Pose Tracking thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Dynamical Binary Latent Variable Models for 3D Human Pose Tracking

Published on Jul 19, 20106034 Views

We introduce a new class of probabilistic latent variable model called the Implicit Mixture of Conditional Restricted Boltzmann Machines (imCRBM) for use in human pose tracking. Key properties of t

Related categories