Texture-aware and Shape-guided Transformer for Sequential DeepFake Detection

arXiv:2404.13873v1 Announce Type: new
Abstract: Sequential DeepFake detection is an emerging task that aims to predict the manipulation sequence in order. Existing methods typically formulate it as an image-to-sequence problem, employing conventional Transformer architectures for detection. However, these methods lack dedicated design and consequently result in limited performance. In this paper, we propose a novel Texture-aware and Shape-guided Transformer to enhance detection performance. Our method features four major improvements. Firstly, we describe a texture-aware branch that effectively captures subtle manipulation …

abstract architectures arxiv cs.cv deepfake design detection however image manipulation paper performance texture transformer type