Attention maps consistently identify eye region, nasolabial folds, and mouth region, areas typically involved in face-swap and reenactment manipulations, providing some evidence that the model's decisions are based on meaningful facial regions, in contrast to basing them on spurious clues.
I. V, Ravali Neela, Bhavishya Chowdary Borra et al.· 2026 10th International Conf...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.