Dimensionality reduction using a Gaussian Process Annealed Particle Filter for tracking and classification of articulated body motions.
Leonid M. RaskinMichael RudzskyEhud RivlinPublished in: Comput. Vis. Image Underst. (2011)
Keyphrases
- gaussian process
- dimensionality reduction
- model selection
- gaussian processes
- body motions
- feature extraction
- decision trees
- hyperparameters
- regression model
- support vector
- cross validation
- feature space
- body parts
- machine learning
- feature selection
- bayesian framework
- mean shift
- latent variables
- closed form
- particle filter
- nearest neighbor
- prior knowledge
- high dimensional