Cross Efficient Vision Transformer

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 ReconstructiononDFDC
AUC· uses extra data· 2021-07-06
0.951
SOTA
Combining EfficientNet and Vision Transformers for Video Deepfake Detection arXiv:2107.02612
3DonDFDC
AUC· uses extra data· 2021-07-06
0.951
SOTA
Combining EfficientNet and Vision Transformers for Video Deepfake Detection arXiv:2107.02612

Audio1 result

DeepFake DetectiononDFDC
AUC· uses extra data· 2021-07-06
0.951
SOTA
Combining EfficientNet and Vision Transformers for Video Deepfake Detection arXiv:2107.02612

Medical1 result

3D Shape Reconstruction from VideosonDFDC
AUC· uses extra data· 2021-07-06
0.951
SOTA
Combining EfficientNet and Vision Transformers for Video Deepfake Detection arXiv:2107.02612