MAAS: Multi-modal Assignation for Active Speaker Detection.

Juan León Alcázar Fabian Caba Heilbron Ali K. Thabet Bernard Ghanem

Published in: ICCV (2021)

Keyphrases

multi modal
audio visual
cross modal
multi modality
semantic concepts
high dimensional
video search
humanoid robot
uni modal
image processing
image analysis
image annotation
fusing multiple