The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation

人体姿态估计中的无偏数据处理.

AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation

AID：通过信息丢弃增强提高人体姿态估计的表现.

High-Performance Large-Scale Image Recognition Without Normalization

NFNet：不使用BatchNorm的大尺度图像分类网络.

PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation

PoseAug：为3D人体姿态估计设计的可微姿态增强框架.

3D Human Pose Estimation = 2D Pose Estimation + Matching

3D人体姿态估计=2D人体姿态估计+匹配.

Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image

单RGB图像3D多人姿态估计的相机距离感知的自顶向下方法.