AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction.

Aggelina Chatziagapi Dimitris Samaras

Published in: CoRR (2023)

Keyphrases

audio visual
multi modal
visual information
visual data
multi stream
temporal context
multimedia
human faces
emotion recognition
audio visual speech recognition
person authentication
multimodal fusion
data sets
search engine
domain knowledge
activity recognition