Multimodal Gesture Recognition Using Multi-stream Recurrent Neural Network.
Noriki NishidaHideki NakayamaPublished in: PSIVT (2015)
Keyphrases
- multi stream
- recurrent neural networks
- audio visual speech recognition
- audio visual
- hidden markov models
- neural network
- reservoir computing
- feed forward
- recurrent networks
- echo state networks
- complex valued
- neural model
- hidden layer
- artificial neural networks
- gesture recognition
- data sets
- multi modal
- feature extraction
- artificial intelligence