A leading-silence artifact in FakeAVCeleb and AV-Deepfake1M lets a trivial classifier separate real from fake, and an unsupervised alignment method trained only on real data avoids relying on this shortcut.
Glitch in the ma- trix: A large scale benchmark for content driven audio-visual forgery detection and localization.Comput
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning
A leading-silence artifact in FakeAVCeleb and AV-Deepfake1M lets a trivial classifier separate real from fake, and an unsupervised alignment method trained only on real data avoids relying on this shortcut.