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

Vladimir Iashin Weidi Xie Esa Rahtu Andrew Zisserman

Published in: BMVC (2022)

Keyphrases

audio visual
multi modal
visual information
temporal context
multimedia
multi stream
emotion recognition
audio visual speech recognition
visual data
video summarization
person authentication
data sets
metadata
three dimensional
space time