https://github.com/BiDAlab/DeepFakesON-Phys
DeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
DeepFake Detection is the task of detecting fake videos or images that have been generated using deep learning techniques. Deepfakes are created by using machine learning algorithms to manipulate or replace parts of an original video or image, such as the face of a person. The goal of deepfake detection is to identify such manipulations and distinguish them from real videos or images.
Description source: DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Image source: DeepFakes: a New Threat to Face Recognition? Assessment and Detection
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
DeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation
Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics
FaceForensics++: Learning to Detect Manipulated Facial Images
AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks
ODDN: Addressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networks
Unmasking Deepfake Faces from Videos Using An Explainable Cost-Sensitive Deep Learning Approach
FaceForensics++: Learning to Detect Manipulated Facial Images
Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images
One-Class Learning with Adaptive Centroid Shift for Audio Deepfake Detection
Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics
D$^3$: Scaling Up Deepfake Detection by Learning from Discrepancy
What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection
FaceForensics++: Learning to Detect Manipulated Facial Images
Generalizable Deepfake Detection via Effective Local-Global Feature Extraction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.