End-To-End Audiovisual Feature Fusion for Active Speaker Detection.

Fiseha B. Tesema Zheyuan Lin Shiqiang Zhu Wei Song Jason Jianjun Gu Hong Wu

Published in: CoRR (2022)

Keyphrases

end to end
feature fusion
text localization and recognition
audio visual
multiple features
feature extraction
visual information
congestion control
real time
multiscale
data mining
multiresolution
multi class
image classification
fusion algorithm