BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge.

Chen Liu Peike Li Hu Zhang Lincheng Li Zi Huang Dadong Wang Xin Yu

Published in: CoRR (2023)

Keyphrases

audio visual
multi modal
domain knowledge
image segmentation
multi stream
audio visual speech recognition
person authentication
e learning
multiscale
feature vectors
image representation
visual information
emotion recognition