Deepfake Detection using Spatiotemporal Convolutional Networks
This work addresses the growing threat of realistic fake videos for security and media integrity, though it appears incremental by focusing on spatiotemporal extensions of existing convolutional approaches.
The paper tackled the problem of detecting deepfake videos by addressing the limitation of existing frame-based methods that ignore temporal information, achieving state-of-the-art performance on the Celeb-DF dataset.
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.