Multimodal Fusion Based on LSTM and a Couple Conditional Hidden Markov Model for Chinese Sign Language Recognition.
Qinkun XiaoMinying QinPeng GuoYidan ZhaoPublished in: IEEE Access (2019)
Keyphrases
- hidden markov models
- sign language recognition
- gesture recognition
- multimodal fusion
- multimodal interfaces
- sign language
- audio visual
- high robustness
- relevance feedback
- hand gestures
- recurrent neural networks
- hand tracking
- word segmentation
- information retrieval
- conditional random fields
- machine learning
- multi modal
- human computer interaction
- image content
- image sequences