AV-PedAware: Self-Supervised Audio-Visual Fusion for Dynamic Pedestrian Awareness.

Yizhuo Yang Shenghai Yuan Muqing Cao Jianfei Yang Lihua Xie

Published in: IROS (2023)

Keyphrases

audio visual
multi modal
multimodal fusion
person authentication
visual information
multi stream
visual data
temporal context
multimedia
emotion recognition
audio visual speech recognition
information fusion
action recognition
spatio temporal
mobile devices
high dimensional
pattern recognition
search engine