Direct Multimodal Few-Shot Learning of Speech and Images.
Leanne NortjeHerman KamperPublished in: Interspeech (2021)
Keyphrases
- image database
- learning process
- input image
- learning algorithm
- ground truth
- edge detection
- image analysis
- audio visual
- three dimensional
- object recognition
- linear predictors
- multi modal
- feature points
- active learning
- supervised learning
- segmentation method
- image collections
- language acquisition
- reinforcement learning