Multimodal Ensemble Model

Reported on 4 benchmarks across 4 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology2 results

3D ReconstructiononFakeAVCeleb
Accuracy (%)
89
best: 99.29 (AV-Lip-Sync+)
3DonFakeAVCeleb
Accuracy (%)
89
best: 99.29 (AV-Lip-Sync+)

Audio1 result

DeepFake DetectiononFakeAVCeleb
Accuracy (%)
89
best: 99.29 (AV-Lip-Sync+)

Medical1 result

3D Shape Reconstruction from VideosonFakeAVCeleb
Accuracy (%)
89
best: 99.29 (AV-Lip-Sync+)