Recurrent Convolutional Strategies for Face Manipulation Detection in Videos
Preprint
Abstract
The spread of misinformation through synthetically generated yet realistic images and videos has become a significant problem, calling for robust manipulation detection methods. Despite the predominant effort of detecting face manipulation in still images, less attention has been paid to the identification of tampered faces in videos by taking advantage of the temporal information present in the stream. Recurrent convolutional models are a class of deep learning models which have proven effective at exploiting the temporal information from image streams across domains. We thereby distill the best strategy for combining variations in these models along with domain specific face preprocessing techniques through extensive experimentation to obtain state-of-the-art performance on publicly available video-based facial manipulation benchmarks. Specifically, we attempt to detect Deepfake, Face2Face and FaceSwap tampered faces in video streams. Evaluation is performed on the recently introduced FaceForensics++ dataset, improving the previous state-of-the-art by up to 4.55% in accuracy.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Face-Specific Data Augmentation for Unconstrained Face RecognitionInternational Journal of Computer Vision, 2019
- Deepfake Video Detection Using Recurrent Neural Networks2018
- BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization2018
- StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation2018
- Coarse-to-Fine Copy-Move Forgery Detection for Video ForensicsIEEE Access, 2018
- Object Detection in Videos with Tubelet Proposal Networks2017
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Deep Residual Learning for Image Recognition2016
- Rethinking the Inception Architecture for Computer Vision2016
- Face2Face: Real-Time Face Capture and Reenactment of RGB Videos2016