Avtenet

Reported on 4 benchmarks across 4 tasks · 1 paper · 4 SOTA

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

Methodology2 results

3D ReconstructiononFakeAVCeleb
Accuracy (%)· 2023-10-19
98.57
best: 99.29 (AV-Lip-Sync+)
SOTA
AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection arXiv:2310.13103
3DonFakeAVCeleb
Accuracy (%)· 2023-10-19
98.57
best: 99.29 (AV-Lip-Sync+)
SOTA
AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection arXiv:2310.13103

Audio1 result

DeepFake DetectiononFakeAVCeleb
Accuracy (%)· 2023-10-19
98.57
best: 99.29 (AV-Lip-Sync+)
SOTA
AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection arXiv:2310.13103

Medical1 result

3D Shape Reconstruction from VideosonFakeAVCeleb
Accuracy (%)· 2023-10-19
98.57
best: 99.29 (AV-Lip-Sync+)
SOTA
AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection arXiv:2310.13103