Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching.

Arsha Nagrani Samuel Albanie Andrew Zisserman

Published in: CVPR (2018)

Keyphrases

cross modal
multi modal
image retrieval
visual recognition
multimedia retrieval
perceptual information
face recognition
keypoints
multimedia databases
image database
contextual information
high level
image sequences
feature extraction
face images
visual data