Convolutional Transformer Fusion Blocks for Multi-Modal Gesture Recognition.
Basavaraj HampiholiChristian JarversWolfgang MaderHeiko NeumannPublished in: IEEE Access (2023)
Keyphrases
- multi modal
- gesture recognition
- multi modality
- hidden markov models
- fusing multiple
- single modality
- hand gestures
- human computer interaction
- sign language recognition
- hand gesture recognition
- hand tracking
- human machine interface
- human robot interaction
- cross modal
- sign language
- high dimensional
- audio visual
- semantic concepts
- image annotation
- neural network
- uni modal
- sign recognition
- humanoid robot
- high level