MSTF, a 143k-video talking face dataset built from 22 forgery techniques, and a global-local audio-visual coherence detector, outperform prior deepfake detectors on this benchmark.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GLCF: A Global-Local Multimodal Coherence Analysis Framework for Talking Face Generation Detection
MSTF, a 143k-video talking face dataset built from 22 forgery techniques, and a global-local audio-visual coherence detector, outperform prior deepfake detectors on this benchmark.