Hearing and Seeing Abnormality: Self-Supervised Audio-Visual Mutual Learning for Deepfake Detection.

Chang-Sung Sung Jun-Cheng Chen Chu-Song Chen

Published in: ICASSP (2023)

Keyphrases

audio visual
databases
multi modal
data sets
spatio temporal
nearest neighbor
visual information
multiscale
co occurrence
dimensionality reduction
visual data
video summarization