Direct multimodal few-shot learning of speech and images.

Leanne Nortje Herman Kamper

Published in: CoRR (2020)

Keyphrases

learning algorithm
image classification
three dimensional
learning process
image database
image data
image registration
reinforcement learning
ground truth
input image
supervised learning
language acquisition
image collections
image set
image features
image analysis
active learning
feature points
multi modal
segmentation method
image regions
test images
video sequences
video retrieval
audio visual
learning mechanism
computer vision