Multimodal One-shot Learning of Speech and Images.
Ryan EloffHerman A. EngelbrechtHerman KamperPublished in: ICASSP (2019)
Keyphrases
- image data
- ground truth
- image analysis
- image registration
- image features
- three dimensional
- image database
- input image
- multiple images
- object recognition
- audio visual
- image classification
- multi modal
- speech recognition
- edge detection
- audio signals
- multiscale
- keypoints
- image collections
- lighting conditions
- image set
- rigid body
- multimodal image registration
- region of interest
- computer graphics
- face images
- d objects
- image retrieval
- image sequences