Existing face forgery detectors mainly focus on specific forgery patterns like noise
characteristics, local textures, or frequency statistics for forgery detection. This causes …

We present a novel one-shot talking head synthesis method that achieves disentangled and
fine-grained control over lip motion, eye gaze&blink, head pose, and emotional expression …

One-shot video-driven talking face generation aims at producing a synthetic talking video by
transferring the facial motion from a video to an arbitrary portrait image. Head pose and …

Talking head generation is to generate video based on a given source identity and target
motion. However, current methods face several challenges that limit the quality and …

Given a source image and a driving video depicting the same object type, the motion
transfer task aims to generate a video by learning the motion from the driving video while …

Existing one-shot face reenactment methods either present obvious artifacts in large pose
transformations, or cannot well-preserve the identity information in the source images, or fail …

Online media data, in the forms of images and videos, are becoming mainstream
communication channels. However, recent advances in deep learning, particularly deep …

Since Facial Action Unit (AU) annotations require domain expertise, common AU datasets
only contain a limited number of subjects. As a result, a crucial challenge for AU detection is …

Unsupervised face animation aims to generate a human face video based on
theappearance of a source image, mimicking the motion from a driving video …

Conventional face forgery detectors have primarily relied on image artifacts produced by
deepfake video generation models. These methods have performed well when the training …