M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection.

Junke Wang Zuxuan Wu Wenhao Ouyang Xintong Han Jingjing Chen Yu-Gang Jiang Ser-Nam Li

Published in: ICMR (2022)

Keyphrases

multi modal
multiscale
audio visual
high dimensional
image annotation
cross modal
multi modality
semantic concepts
multimedia
image segmentation
video search
single modality
fusing multiple