Manipulation detection on FakeAVCeleb (FVFA-FS)
100APFTCN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| FTCNModality=Visual, Pretrained dataset=None, Supervision Protocol=Supervised2023.01 | 100 | 100 | |
| FTCNModality=V2024.06 | 100 | 100 | |
| AVFFModality=AV2024.06 | 100 | 100 | |
| LipForensicsModality=Visual, Pretrained dataset=LRW, Supervision Protocol=Supervised2023.01 | 99.9 | 99.9 | |
| LipForensicsModality=V2024.06 | 99.9 | 99.9 | |
| AD DFDModality=Audio-Visual, Pretrained dataset=Kinetics, Supervision Protocol=Supervised2023.01 | 99.6 | 99.7 | |
| AV-DFDModality=AV2024.06 | 99.6 | 99.7 | |
| RealForensicsModality=Visual, Pretrained dataset=LRW, Supervision Protocol=Supervised2023.01 | 99.3 | 99.1 | |
| RealForensicsModality=V2024.06 | 99.3 | 99.1 | |
| Audio-Visual Anomaly Detection (Ours)Modality=Audio-Visual, Pretrained dataset=LRS2, Supervision Protocol=Unsupervised2023.01 | 95.3 | 95.8 | |
| AVADModality=AV, Training Set=LRS22024.06 | 95.3 | 95.8 | |
| XceptionModality=Visual, Pretrained dataset=ImageNet, Supervision Protocol=Supervised2023.01 | 92.3 | 93.5 | |
| XceptionModality=V2024.06 | 92.3 | 93.5 | |
| Audio-Visual Anomaly Detection (Ours)Modality=Audio-Visual, Pretrained dataset=LRS3, Supervision Protocol=Unsupervised2023.01 | 91 | 92.3 | |
| AVADModality=AV, Training Set=LRS32024.06 | 91 | 92.3 | |
| AVBYOLModality=Audio-Visual, Pretrained dataset=LRW, Supervision Protocol=Unsupervised2023.01 | 88.7 | 80.8 | |
| VQ-GANModality=Visual, Pretrained dataset=LRS2, Supervision Protocol=Unsupervised2023.01 | 57.5 | 53 |