A Variational Bayesian Labeled Multi-Bernoulli Filter for Tracking with Inverse Wishart Distribution.
Jinran WangZhongliang JingPeng DongJin ChengPublished in: FUSION (2018)
Keyphrases
- exponential family
- variational bayesian
- order statistics
- maximum likelihood
- graphical models
- statistical models
- density estimation
- closed form
- log likelihood
- missing values
- mixture model
- dirichlet process
- variational methods
- variational inference
- particle filter
- markov chain monte carlo
- probability density function
- object tracking
- density function
- motion model
- random variables
- hidden variables
- noise reduction
- multi task learning
- median filter
- factor analysis
- posterior distribution
- incomplete data
- matrix factorization
- training data
- visual tracking
- parameter estimation
- generative model
- expectation maximization
- supervised learning
- active learning