Deepfake Detection using ImageNet models and Temporal Images of 468 Facial Landmarks
This addresses deepfake detection for security applications, but appears incremental as it applies existing models to a new data representation.
The paper tackled deepfake detection by modeling temporal facial landmark movements as spatial images and testing 10 ImageNet models, achieving unspecified results without concrete numbers.
This paper presents our results and findings on the use of temporal images for deepfake detection. We modelled temporal relations that exist in the movement of 468 facial landmarks across frames of a given video as spatial relations by constructing an image (referred to as temporal image) using the pixel values at these facial landmarks. CNNs are capable of recognizing spatial relationships that exist between the pixels of a given image. 10 different ImageNet models were considered for the study.