论文标题
Zoomnas：在野外寻找全身人类姿势估计
ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
论文作者
论文摘要
本文研究了2D全身姿势估计的任务，该任务旨在将整个人体（包括身体，脚，脸部和手）的密集地标定位。我们提出了一种称为Zoomnet的单网络方法，以考虑到完整人体的层次结构，并解决不同身体部位的规模变化。我们进一步提出了一个称为Zoomnas的神经体系结构搜索框架，以促进全身姿势估计的准确性和效率。 Zoomnas共同搜索模型架构和不同子模块之间的连接，并自动为搜索的子模块分配计算复杂性。为了培训和评估Zoomnas，我们介绍了第一个大型2D人类全身数据集，即可可叶全体v1.0，它注释了133个用于野外图像的关键点。广泛的实验证明了Zoomnas的有效性和可可叶v1.0的意义。
This paper investigates the task of 2D whole-body human pose estimation, which aims to localize dense landmarks on the entire human body including body, feet, face, and hands. We propose a single-network approach, termed ZoomNet, to take into account the hierarchical structure of the full human body and solve the scale variation of different body parts. We further propose a neural architecture search framework, termed ZoomNAS, to promote both the accuracy and efficiency of whole-body pose estimation. ZoomNAS jointly searches the model architecture and the connections between different sub-modules, and automatically allocates computational complexity for searched sub-modules. To train and evaluate ZoomNAS, we introduce the first large-scale 2D human whole-body dataset, namely COCO-WholeBody V1.0, which annotates 133 keypoints for in-the-wild images. Extensive experiments demonstrate the effectiveness of ZoomNAS and the significance of COCO-WholeBody V1.0.
