Multimodal Variational Auto-encoder based Audio-Visual Segmentation.

Yuxin Mao Jing Zhang Mochu Xiang Yiran Zhong Yuchao Dai

Published in: ICCV (2023)

Keyphrases

audio visual
image segmentation
multi modal
multi stream
visual information
multimodal fusion
multimedia
multiscale
visual data
level set
bit rate
audio features
audio visual speech recognition
image processing
spatio temporal
person authentication