TL;DR研究单阶段方法与多阶段方法在姿态估计领域的性能表现，提出了单阶段模块设计、跨阶段特征聚合和粗到细的监督等改进建议，所得方法在MS COCO和MPII Human Pose数据集上都取得了新的最优表现，证明了多阶段架构的有效性。
Abstract
Existing pose estimation approaches can be categorized into single-stage and multi-stage methods. While a multi-stage architecture is seemingly more suitable for the task, the →