FakeAVCeleb is a novel Audio-Video Deepfake dataset that not only contains deepfake videos but respective synthesized cloned audios as well.
Image source: https://arxiv.org/pdf/2108.05080v1.pdf
Variants: FakeAVCeleb
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| DeepFake Detection | AV-Lip-Sync+ | AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit … | 2023-11-05 |
| DeepFake Detection | FACTOR | Detecting Deepfakes Without Seeing Any | 2023-11-02 |
| DeepFake Detection | Avtenet | AVTENet: Audio-Visual Transformer-based Ensemble Network … | 2023-10-19 |
| DeepFake Detection | AVAD | Self-Supervised Video Forensics by Audio-Visual … | 2023-01-04 |
| DeepFake Detection | AVBYOL | Leveraging Real Talking Faces via … | 2022-01-18 |
| DeepFake Detection | RealForensics | Leveraging Real Talking Faces via … | 2022-01-18 |
| DeepFake Detection | FTCN | Exploring Temporal Coherence for More … | 2021-08-15 |
| DeepFake Detection | VQGAN | Taming Transformers for High-Resolution Image … | 2020-12-17 |
| DeepFake Detection | LipForensics | Lips Don't Lie: A Generalisable … | 2020-12-14 |
| DeepFake Detection | Xception | FaceForensics++: Learning to Detect Manipulated … | 2019-01-25 |
Recent papers with results on this dataset: