Statistics-aware Audio-visual Deepfake Detector.

Marcella Astrid Enjie Ghorbel Djamila Aouada

Published in: CoRR (2024)

Keyphrases

audio visual
multi modal
visual information
multimedia
multi stream
temporal context
visual data
person authentication
video summarization
multimodal fusion
emotion recognition
knowledge base
pose estimation
low level
multiscale
spatio temporal
feature extraction
feature selection
audio visual speech recognition