HyperAI초신경

홈 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Deepfake Detection On Fakeavceleb 1

평가 지표

AP

ROC AUC

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	AP	ROC AUC	Paper Title	Repository
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
FACTOR	96.8	97.4	Detecting Deepfakes Without Seeing Any
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	-
RealForensics	95.3	97.1	Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection
VQGAN	55.0	51.8	Taming Transformers for High-Resolution Image Synthesis
AVBYOL	73.9	59.2	Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection
Avtenet	-	-	AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection	-
Xception	84.8	85.3	FaceForensics++: Learning to Detect Manipulated Facial Images
LipForensics	89.4	91.1	Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection
AV-Lip-Sync Model	-	-	Lip Sync Matters: A Novel Multimodal Forgery Detector	-
AD DFD	88.8	88.1	Joint Audio-Visual Deepfake Detection	-

0 of 13 row(s) selected.