Multi-Modal Continual Pre-Training For Audio Encoders.

Gyuhak Kim Ho-Hsiang Wu Luca Bondi Bing Liu

Published in: ICASSP (2024)

Keyphrases

multi modal
audio visual
cross modal
single modality
multi modality
training set
high dimensional
humanoid robot
multimedia
visual information
semantic concepts
video search
image annotation
computer vision
keywords