论文标题
使用时空卷积网络进行深泡检测
Deepfake Detection using Spatiotemporal Convolutional Networks
论文作者
论文摘要
更好的生成模型和较大的数据集导致了更逼真的虚假视频，这些视频可能会欺骗人的眼睛，但会产生深度学习方法可以检测到的时间和空间文物。当前大多数DeepFake检测方法仅使用单个视频帧，因此无法从时间信息中学习。我们创建了使用Celeb-DF数据集的时空卷积方法性能的基准。我们的方法优于基于最新框架的检测方法。我们的论文代码可在https://github.com/oidelima/deepfake-detection上公开获得。
Better generative models and larger datasets have led to more realistic fake videos that can fool the human eye but produce temporal and spatial artifacts that deep learning approaches can detect. Most current Deepfake detection methods only use individual video frames and therefore fail to learn from temporal information. We created a benchmark of the performance of spatiotemporal convolutional methods using the Celeb-DF dataset. Our methods outperformed state-of-the-art frame-based detection methods. Code for our paper is publicly available at https://github.com/oidelima/Deepfake-Detection.
