https://github.com/wentianzhang-ml/frt-pad
공식 코드FRT-PAD: Effective Presentation Attack Detection Driven by Face Related Task
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.
FRT-PAD: Effective Presentation Attack Detection Driven by Face Related Task
Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video
Fairness Properties of Face Recognition and Obfuscation Systems
MiVOLO: Multi-input Transformer for Age and Gender Estimation
VToonify: Controllable High-Resolution Portrait Video Style Transfer
Robust Sclera Segmentation for Skin-tone Agnostic Face Image Quality Assessment
FFR_FD: Effective and Fast Detection of DeepFakes Based on Feature Point Defects
Kernel Principal Component Analysis and its Applications in Face Recognition and Active Shape Models
Imitating Arbitrary Talking Style for Realistic Audio-DrivenTalking Face Synthesis
Reference-Guided Large-Scale Face Inpainting with Identity and Texture Control
iTARGET: Interpretable Tailored Age Regression for Grouped Epigenetic Traits
Mitigating Unauthorized Speech Synthesis for Voice Protection
SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis
Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimodal Emotion Recognition
RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs
MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles
ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification
Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues
The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio
Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception
Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio?
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.