Seeing Voices and Hearing Faces: Cross-modal biometric matching.

Arsha Nagrani Samuel Albanie Andrew Zisserman

Published in: CoRR (2018)

Keyphrases

cross modal
multi modal
multimedia retrieval
image retrieval
perceptual information
face recognition
visual similarity
visual data
multimedia databases
image matching
visual recognition
video sequences
semantic similarity
image set
keypoints
feature extraction
multimedia