3.8 Proceedings Paper

Fighting Against Deepfake: Patch&Pair Convolutional Neural Networks (PPCNN)

出版社

ASSOC COMPUTING MACHINERY
DOI: 10.1145/3366424.3382711

关键词

Deepfake videos; Tampering detection; Multi-task learning

向作者/读者索取更多资源

In this paper, we propose a novel Patch&Pair Convolutional Neural Networks (PPCNN) to distinguish Deepfake videos or images from real ones. Through the comprehensive evaluations on public datasets, we demonstrate that our model performs better than existing detection methods and show better generalization.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

3.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据