Graph-Regularized Attentive Convolutional Entanglement for Robust DeepFake Video Detection

doi:doi:10.57702/jfv5oja4

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.

BibTex:

@dataset{Chih-Chung_Hsu_and_Shao-Ning_Chen_and_Mei-Hsuan_Wu_and_Yi-Fang_Wang_and_Chia-Ming_Lee_and_Yi-Shiuan_Chou_2024,
    abstract = {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.},
    author = {Chih-Chung Hsu and Shao-Ning Chen and Mei-Hsuan Wu and Yi-Fang Wang and Chia-Ming Lee and Yi-Shiuan Chou},
    doi = {10.57702/jfv5oja4},
    institution = {No Organization},
    keyword = {'Deepfake', 'Face Sequences', 'Graph Convolutional Network', 'Graph Laplacian Smoothing', 'Video Detection'},
    month = {dec},
    publisher = {TIB},
    title = {Graph-Regularized Attentive Convolutional Entanglement for Robust DeepFake Video Detection},
    url = {https://service.tib.eu/ldmservice/dataset/graph-regularized-attentive-convolutional-entanglement-for-robust-deepfake-video-detection},
    year = {2024}
}