Audio-to-Image Cross-Modal Generation.

Maciej Zelaszczyk Jacek Mandziuk

Published in: IJCNN (2022)

Keyphrases

cross modal
image retrieval
multi modal
image data
visual data
visual similarity
image features
image content
image representation
image collections
multiscale
image classification
image segmentation
low level
image regions
multimedia retrieval
high level
keypoints
test images
perceptual information
image database
content based retrieval
contextual information
computer vision