https://github.com/aimagelab/COCOFake
공식 코드Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images
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.
Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images
Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities
Face Verification with Challenging Imposters and Diversified Demographics
GANimation: Anatomically-aware Facial Animation from a Single Image
DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models
It's All in the Head: Representation Knowledge Distillation through Classifier Sharing
Learning from Failure: Training Debiased Classifier from Biased Classifier
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation
ACR Loss: Adaptive Coordinate-based Regression Loss for Face Alignment
GANalyzer: Analysis and Manipulation of GANs Latent Space for Controllable Face Synthesis
Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks
Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition Model
Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition
Faithful Target Attribute Prediction in Neural Machine Translation
Robustness Analysis of Deep Learning Frameworks on Mobile Platforms
FastFace: Fast-converging Scheduler for Large-scale Face Recognition Training with One GPU
UnMarker: A Universal Attack on Defensive Image Watermarking
Shape Preserving Facial Landmarks with Graph Attention Networks
Unsupervised Single-shot Depth Estimation using Perceptual Reconstruction
Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers
Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection
On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofing
Extending Information Bottleneck Attribution to Video Sequences
SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes
AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detection
Laughing Matters: Introducing Laughing-Face Generation using Diffusion Models
A Dataless FaceSwap Detection Approach Using Synthetic Images
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.