Dynamical binary latent variable models for 3D human pose tracking
Computer Vision and Pattern Recognition, 2010, Pages 631-638.
Boltzmann machinesfiltering theoryimage motion analysispose estimationprobabilityMore(8+)
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
Full Text (Upload PDF)
PPT (Upload PPT)