Making the Coupled Gaussian Process Dynamical Model Modular and Scalable with Variational Approximations.
Dmytro VelychkoBenjamin KnoppDominik EndresPublished in: Entropy (2018)
Keyphrases
- dynamical model
- gaussian process
- gaussian processes
- dynamical models
- regression model
- bayesian framework
- latent variables
- model selection
- semi supervised
- latent space
- hyperparameters
- computer vision
- human motion
- autoregressive
- subject specific
- image segmentation
- closed form
- optical flow
- human body
- maximum a posteriori
- active learning