Perception Updating Networks: On architectural constraints for interpretable video generative models.
Eder SantanaJosé C. PríncipePublished in: ICLR (Workshop) (2017)
Keyphrases
- generative model
- probabilistic model
- mixture model
- discriminative learning
- video sequences
- discriminative models
- discriminative learning framework
- hierarchical hidden markov models
- video data
- maximum entropy principle
- em algorithm
- object categories
- discriminative methods
- dynamic textures
- hidden variables
- generative and discriminative models
- graphical models
- conditional random fields
- network structure
- representational power
- information retrieval
- topic models
- computer vision