Semantic Graph Convolutional Networks for 3D Human Pose Regression
Semantic Graph Convolutional Networks for 3D Human Pose Regression
复制标题
DOI：
10.1109/cvpr.2019.00354
复制
发表时间：
2019-04
期刊：
影响因子：
--
通讯作者：
Long Zhao;Xi Peng;Yu Tian;Mubbasir Kapadia;Dimitris N. Metaxas
中科院分区：
文献类型：
--
作者：
Long Zhao;Xi Peng;Yu Tian;Mubbasir Kapadia;Dimitris N. Metaxas
在本文中，我们研究了学习图卷积网络（GCN）回归的问题。目前的GCN结构仅限于卷积滤波器的小接收域和每个节点的共享变换矩阵。为了解决这些限制，我们提出了语义图卷积网络（SemGCN），这是一种新型的神经网络架构，可以使用图结构数据进行回归任务。SemGCN学习捕获语义信息，如局部和全局节点关系，这些信息在图中没有显式表示。这些语义关系可以通过端到端的训练从地面事实中学习，而无需额外的监督或手工制定的规则。我们进一步研究将SemGCN应用于3D人体姿势回归。我们的配方是直观的和足够的，因为2D和3D人体姿势可以表示为一个结构化的图形编码的关节之间的关系在人体的骨架。我们进行了全面的研究，以验证我们的方法。结果证明，SemGCN优于现有技术，同时使用少90%的参数。
In this paper, we study the problem of learning Graph Convolutional Networks (GCNs) for regression. Current architectures of GCNs are limited to the small receptive field of convolution filters and shared transformation matrix for each node. To address these limitations, we propose Semantic Graph Convolutional Networks (SemGCN), a novel neural network architecture that operates on regression tasks with graph-structured data. SemGCN learns to capture semantic information such as local and global node relationships, which is not explicitly represented in the graph. These semantic relationships can be learned through end-to-end training from the ground truth without additional supervision or hand-crafted rules. We further investigate applying SemGCN to 3D human pose regression. Our formulation is intuitive and sufficient since both 2D and 3D human poses can be represented as a structured graph encoding the relationships between joints in the skeleton of a human body. We carry out comprehensive studies to validate our method. The results prove that SemGCN outperforms state of the art while using 90% fewer parameters.