https://github.com/yangyucheng000/-insightface
Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression
RCR: Robust Compound Regression for Robust Estimation of Errors-in-Variables Model
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
Age Progression/Regression by Conditional Adversarial Autoencoder
Automated Problem Identification: Regression vs Classification via Evolutionary Deep Networks
Meta-Learning Priors for Efficient Online Bayesian Regression
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Variational AutoEncoder For Regression: Application to Brain Aging Analysis
Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching
One-step and Two-step Classification for Abusive Language Detection on Twitter
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language
Simultaneous Transformation and Rounding (STAR) Models for Integer-Valued Data
Personalized Gaussian Processes for Future Prediction of Alzheimer's Disease Progression
Group-aware Contrastive Regression for Action Quality Assessment
SPSA-FSR: Simultaneous Perturbation Stochastic Approximation for Feature Selection and Ranking
Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking
MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis
Semantic Graph Convolutional Networks for 3D Human Pose Regression
Bayesian inference for logistic models using Polya-Gamma latent variables
Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression
End-to-End Learning of Geometry and Context for Deep Stereo Regression
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.