Sparse in Space and Time: Audio-visual Synchronisation with Trainable Selectors.

Vladimir Iashin Weidi Xie Esa Rahtu Andrew Zisserman

Published in: CoRR (2022)

Keyphrases

audio visual
multi modal
high dimensional
multi stream
visual information
visual data
low dimensional
emotion recognition
multimedia
audio visual speech recognition
space time
multimodal fusion
pattern recognition
domain knowledge