Restore DeepFakes video frames via identifying individual motion styles

Abstract Recent advance on highly realistic AI‐synthesised video approaches makes it hard to distinguish whether a speaker in video is real. Many existing DeepFakes detection approaches can be invalidated by using them as supervision in adversarial training, which in turn improves the performance of...

Full description

Bibliographic Details

Published in:	Electronics Letters
Main Authors:	Haichao Zhang, Zhe‐Ming Lu, Hao Luo, Ya‐Pei Feng
Format:	Article
Language:	English
Published:	Wiley 2021-02-01
Subjects:	Speech and audio signal processing Optical, image and video signal processing Computer vision and image processing techniques Video signal processing Speech processing techniques
Online Access:	https://doi.org/10.1049/ell2.12015