Abstract
Spread of misinformation has become a significant problem, raising the importance of relevant detection methods. While there are different manifestations of misinformation, in this work we focus on detecting face manipulations in videos. Specifically, we attempt to detect Deepfake, Face2Face and FaceSwap manipulations in videos. We exploit the temporal dynamics of videos with a recurrent approach. Evaluation is done on FaceForensics++ dataset and our method improves upon the previous state-of-the-art up to 4.55%.
Abstract (translated)
误报传播已成为一个重要问题,提高了相关检测方法的重要性。虽然有不同的表现形式的错误信息,在这项工作中,我们集中在检测面部操纵视频。具体来说,我们尝试在视频中检测deepfake、face2face和faceswap操作。我们用一种反复的方法利用视频的时间动态。对FaceForensics++数据集进行评估,我们的方法比以前的最先进水平提高了4.55%。
URL
https://arxiv.org/abs/1905.00582