2

AI Killed the Video Star. Audio-Driven Diffusion Model for Expressive Talking Head Generation
Dimitra++, a conditional Motion Diffusion Transformer that generates expressive talking head videos (lip motion, facial expression and head pose) from a single reference image and audio.
Baptiste Chopin, Tashvik Dhamija, Pranav Balaji, Yaohui Wang, Antitza Dantcheva
Project arXiv
Do You See What I Say? Generalizable Deepfake Detection based on Visual Speech Recognition
FauxNet uses pre-trained visual speech recognition features for zero-shot deepfake detection and attribution, evaluated on the new Authentica datasets and FaceForensics++.
Maheswar Bora, Tashvik Dhamija, Shukesh Reddy, Baptiste Chopin, Pranav Balaji, Abhijit Das, Antitza Dantcheva
Dataset arXiv