AV-Deepfake1M++ is a 2.05-million-clip audio-visual deepfake benchmark spanning three source corpora, nine generators, and 36 perturbations, with challenge results showing large generalization gaps.
Shulby, Arnaldo Candido Junior, Eren Gölge, and Moacir A
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbations
AV-Deepfake1M++ is a 2.05-million-clip audio-visual deepfake benchmark spanning three source corpora, nine generators, and 36 perturbations, with challenge results showing large generalization gaps.