Face-Voice Matching using Cross-modal Embeddings.

Shota Horiguchi Naoyuki Kanda Kenji Nagamatsu

Published in: ACM Multimedia (2018)

Keyphrases

cross modal
multi modal
image retrieval
multimedia retrieval
multimedia databases
keypoints
vector space
image set
visual recognition
perceptual information
face images
low dimensional
image matching
visual data