Layered dynamic mixture model for pattern discovery in asynchronous multi-modal streams [video applications].
Lexing XieLyndon S. KennedyShih-Fu ChangAjay DivakaranHuifang SunChing-Yung LinPublished in: ICASSP (2) (2005)
Keyphrases
- multi modal
- mixture model
- pattern discovery
- semantic concepts
- em algorithm
- video search
- gaussian mixture model
- pattern mining
- model selection
- generative model
- expectation maximization
- probabilistic model
- video sequences
- association rule mining
- sequential patterns
- video data
- data analysis
- language model
- maximum likelihood
- multiple modalities
- data mining
- unsupervised learning
- multimedia
- audio visual
- computer vision
- data sets
- text mining
- feature vectors
- data streams
- bayesian networks
- video retrieval
- video shots