eduzhai > Applied Sciences > Engineering >

Deepfake Detection using Spatiotemporal Convolutional Networks

  • Save

... pages left unread,continue reading

Document pages: 6 pages

Abstract: Better generative models and larger datasets have led to more realistic fakevideos that can fool the human eye but produce temporal and spatial artifactsthat deep learning approaches can detect. Most current Deepfake detectionmethods only use individual video frames and therefore fail to learn fromtemporal information. We created a benchmark of the performance ofspatiotemporal convolutional methods using the Celeb-DF dataset. Our methodsoutperformed state-of-the-art frame-based detection methods. Code for our paperis publicly available at this https URL.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×