Can Audio-Visual Integration Strengthen Robustness Under Multimodal Attacks?

Yapeng Tian Chenliang Xu

Published in: CVPR (2021)

Keyphrases

audio visual
multi modal
visual information
multimodal fusion
multi stream
emotion recognition
visual data
high robustness
multimedia
temporal context
person authentication
audio visual speech recognition
databases
three dimensional
high level
image database