Learning Expressive And Generalizable Motion Features For Face Forgery Detection

arXiv:2403.05172v1 Announce Type: new
Abstract: Previous face forgery detection methods mainly focus on appearance features, which may be easily attacked by sophisticated manipulation. Considering the majority of current face manipulation methods generate fake faces based on a single frame, which do not take frame consistency and coordination into consideration, artifacts on frame sequences are more effective for face forgery detection. However, current sequence-based face forgery detection methods use general video classification networks directly, which discard the special and discriminative motion …

abstract arxiv cs.cv current detection detection methods face face manipulation fake features focus forgery generate manipulation type