Deepfake Detection On Fakeavceleb 1

Métriques

AP

ROC AUC

Résultats

Résultats de performance de divers modèles sur ce benchmark

			Paper Title
FACTOR	96.8	97.4	Detecting Deepfakes Without Seeing Any
RealForensics	95.3	97.1	Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection
AVAD	94.2	94.5	Self-Supervised Video Forensics by Audio-Visual Anomaly Detection
FTCN	92.3	93.1	Exploring Temporal Coherence for More General Video Face Forgery Detection
LipForensics	89.4	91.1	Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection
AD DFD	88.8	88.1	Joint Audio-Visual Deepfake Detection
Xception	84.8	85.3	FaceForensics++: Learning to Detect Manipulated Facial Images
AVBYOL	73.9	59.2	Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection
VQGAN	55.0	51.8	Taming Transformers for High-Resolution Image Synthesis
AV-Lip-Sync+	-	-	AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Video Deepfake Detection
Multimodal Ensemble Model	-	-	Lip Sync Matters: A Novel Multimodal Forgery Detector
Avtenet	-	-	AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection
AV-Lip-Sync Model	-	-	Lip Sync Matters: A Novel Multimodal Forgery Detector

0 of 13 row(s) selected.