Audio-visual human recognition using semi-supervised spectral learning and hidden Markov models.
Wei FengLei XieJia ZengZhi-Qiang LiuPublished in: J. Vis. Lang. Comput. (2009)
Keyphrases
- hidden markov models
- audio visual
- semi supervised
- multi stream
- sequence classification
- speech recognition
- continuous hidden markov models
- hidden state
- multi modal
- learning algorithm
- semi supervised learning
- contextual information
- visual data
- gesture recognition
- em algorithm
- natural language processing
- active learning
- computer vision