Deepfake Detection using Spatiotemporal Convolutional Networks

Abstract

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.

References in corpus (9)

• The Kinetics Human Action Video Dataset
• MesoNet: a Compact Facial Video Forgery Detection Network
• DeepFakes: a New Threat to Face Recognition? Assessment and Detection
• RetinaFace: Single-stage Dense Face Localisation in the Wild
• Automatic Face Reenactment
• Unmasking DeepFakes with simple Features
• The Deepfake Detection Challenge (DFDC) Preview Dataset
• Use of a Capsule Network to Detect Fake Images and Videos
• Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network

Cited by in corpus (5)

• Combining EfficientNet and Vision Transformers for Video Deepfake Detection
• FedForgery: Generalized Face Forgery Detection with Residual Federated Learning
• Deepfake Detection Scheme Based on Vision Transformer and Distillation
• Video Transformer for Deepfake Detection with Incremental Learning
• Challenges and Solutions in DeepFakes