https://github.com/niuxiaozhang/mxnet-retinaface-to-gluon
RetinaFace: Single-stage Dense Face Localisation in the Wild
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.
RetinaFace: Single-stage Dense Face Localisation in the Wild
FaceNet: A Unified Embedding for Face Recognition and Clustering
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
FaceNet: A Unified Embedding for Face Recognition and Clustering
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
Self-supervised learning of a facial attribute embedding from video
FaceNet: A Unified Embedding for Face Recognition and Clustering
Challenges in Representation Learning: A report on three machine learning contests
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network
Automatic Recognition of Student Engagement using Deep Learning and Facial Expression
Automatic Recognition of Student Engagement using Deep Learning and Facial Expression
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
PetFace: A Large-Scale Dataset and Benchmark for Animal Identification
Progressive Growing of GANs for Improved Quality, Stability, and Variation
BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation
DeepFaceLab: Integrated, flexible and extensible face-swapping framework
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
Deep High-Resolution Representation Learning for Visual Recognition
SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
Compacting, Picking and Growing for Unforgetting Continual Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.