Graph-Regularized Attentive Convolutional Entanglement for Robust DeepFake Video Detection

The proposed GRACE method leverages feature entanglement with sparse constraints and a graph convolutional network with graph Laplacian smoothing prior regularization to effectively exploit the spatial-temporal correlations in face sequences while suppressing the impact of noise and distortions.

Data and Resources

Cite this as

Chih-Chung Hsu, Shao-Ning Chen, Mei-Hsuan Wu, Yi-Fang Wang, Chia-Ming Lee, Yi-Shiuan Chou (2024). Dataset: Graph-Regularized Attentive Convolutional Entanglement for Robust DeepFake Video Detection. https://doi.org/10.57702/jfv5oja4

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2406.19941
Author Chih-Chung Hsu
More Authors
Shao-Ning Chen
Mei-Hsuan Wu
Yi-Fang Wang
Chia-Ming Lee
Yi-Shiuan Chou
Homepage https://github.com/ming053l/GRACE