Recently, most existing human pose estimation methods fuse multi-stage convolutional modules to learn a shared feature representation. In this paper, we propose a expectation–maximization (EM) mapping-based network to learn specific related body parts for human pose estimation, named EMposeNet. It maps specific feature of related parts from the original fully shared feature space. From the perspective of multi-task learning, we can regard the task of human pose estimation as a homogeneous multi-task learning. Sharing features among related tasks can result in a more compact model and better generalization ability. However, sharing features for those unrelated or weakly related tasks will deteriorate the estimation performance. Our proposed method aims at performing EM algorithm to learn the related body part, where the predicted keypoint heatmap is potentially more accurate and spatially more precise. We conduct extensive experiments on two benchmark datasets, including the MSCOCO keypoint detection dataset and the MPII human pose dataset, to empirically demonstrate the validity of the proposed method. The results on such two benchmark datasets show that the proposed approach achieves a competitive performance.

最近，大多数现有的人体姿势估计方法融合了多级卷积模块，以学习共享的特征表示。在本文中，我们提出了一种基于期望最大化（EM）映射的网络，以学习用于人体姿势估计的特定相关身体部位，称为EMposeNet。它从原始的完全共享的特征空间中映射了相关零件的特定特征。从多任务学习的角度来看，我们可以将人体姿势估计任务视为同类的多任务学习。在相关任务之间共享功能可以使模型更紧凑，泛化能力更好。但是，为那些不相关或关联性较弱的任务共享功能会降低估计性能。我们提出的方法旨在执行EM算法来学习相关的身体部位，预测的关键点热点图可能更准确，空间上更精确。我们对两个基准数据集（包括MSCOCO关键点检测数据集和MPII人类姿态数据集）进行了广泛的实验，以从经验上证明了该方法的有效性。在这两个基准数据集上的结果表明，所提出的方法具有竞争优势。