List your company
ResearchFormerly WizWand

Deepfake Detection on NeuralTextures (NT) (test)

94.92AUC (%)QAD-E
69.252875.916482.5889.2436Sep 12, 2023
Updated 8mo ago

Evaluation results

MethodLinks
QAD-ESetting=Quality-agnostic, Compression=Video (raw + c23 + c40)2023.0994.92
QAD-RSetting=Quality-agnostic, Compression=Video (raw + c23 + c40)2023.0991.25
Rössler et al.Setting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=published code2023.0989.64
Fang & LinSetting=Quality-agnostic, Compression=Video (raw + c23 + c40)2023.0989.3
F3NetSetting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=published code2023.0986.79
MATSetting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=published code2023.0986.79
ADDSetting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=pre-trained weights2023.0986.26
BZNetSetting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=pre-trained weights2023.0980.12
SBIsSetting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=pre-trained weights2023.0978.33
MesoNetSetting=Quality-agnostic, Compression=Video (raw + c23 + c40)2023.0970.24