Flow2Flow: Audio-visual cross-modality generation for talking face videos with rhythmic head.

Zhangjing Wang Wenzhi He Yujiang Wei Yupeng Luo

Published in: Displays (2023)

Keyphrases

audio visual
multi modal
person authentication
visual data
video summarization
high level
multimodal fusion
video sequences
visual information
audio features
temporal context
data sets
multimedia
video data
multi stream