Watch, Listen Once, and Sync: Audio-Visual Synchronization With Multi-Modal Regression Cnn.

Toshiki Kikuchi Yuko Ozasa

Published in: ICASSP (2018)

Keyphrases

multi modal
audio visual
multi stream
multi modality
audio visual speech recognition
cross modal
image annotation
high dimensional
audio features
domain knowledge
video search
computer vision
high level
data management