https://github.com/qiqitao77/awesome-comprehensive-deepfake-detection
공식 코드Evolving from Single-modal to Multi-modal Facial Deepfake Detection: A Survey
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Facial tasks in machine learning operate based on images or video frames (or other datasets) focussed on human faces.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Evolving from Single-modal to Multi-modal Facial Deepfake Detection: A Survey
Evolving from Single-modal to Multi-modal Facial Deepfake Detection: A Survey
Transferable Class-Modelling for Decentralized Source Attribution of GAN-Generated Images
Deepfake for the Good: Generating Avatars through Face-Swapping with Implicit Deepfake Generation
Fairness Under Cover: Evaluating the Impact of Occlusions on Demographic Bias in Facial Recognition
Open-set Face Recognition with Neural Ensemble, Maximal Entropy Loss and Feature Augmentation
AVT2-DWF: Improving Deepfake Detection with Audio-Visual Fusion and Dynamic Weighting Strategies
Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection
SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition
XAI-Based Detection of Adversarial Attacks on Deepfake Detectors
AWARE-NET: Adaptive Weighted Averaging for Robust Ensemble Network in Deepfake Detection
DAA: A Delta Age AdaIN operation for age estimation via binary code transformer
RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars
Perturbation Inactivation Based Adversarial Defense for Face Recognition
Descriptor: Face Detection Dataset for Programmable Threshold-Based Sparse-Vision
XMAD-Bench: Cross-Domain Multilingual Audio Deepfake Benchmark
Individualized Deepfake Detection Exploiting Traces Due to Double Neural-Network Operations
Local Sliced-Wasserstein Feature Sets for Illumination-invariant Face Recognition
Predicting Gender by First Name Using Character-level Machine Learning
StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.