CAD - Contextual Multi-modal Alignment for Dynamic AVQA.

Asmar Nadeem Adrian Hilton Robert Dawes Graham Thomas Armin Mustafa

Published in: WACV (2024)

Keyphrases

multi modal
multi modality
high dimensional
audio visual
cross modal
semantic concepts
fusing multiple
metadata
contextual information
video search
image analysis
higher level
image annotation
humanoid robot
multiple modalities
uni modal