arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.03328cs.CV
收藏

基于图卷积网络的动作识别的学习连通性

Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition

Sorbonne University(索邦大学);CNRS(法国国家科学研究中心);LIP6(巴黎第六大学计算机科学实验室)

Hichem Sahbi

摘要:

学习图卷积网络(GCN)是一个新兴的领域,旨在将卷积运算推广到任意非正则域。特别是,在空间域上操作的GCN显示出比谱域更优越的性能,但是它们的成功高度依赖于如何定义输入图的拓扑结构。在本文中,我们介绍了一种新的图卷积网络的框架,学习图的拓扑性质。我们的方法的设计原理是基于约束目标函数的优化,该函数不仅学习GCN中的常用卷积参数,还学习传达这些图中最相关拓扑关系的变换基础。在具有挑战性的基于图的动作识别任务上进行的实验表明,与手工图设计以及相关工作相比,所提出的方法具有优越性。

英文摘要:

Learning graph convolutional networks (GCNs) is an emerging field which aims at generalizing convolutional operations to arbitrary non-regular domains. In particular, GCNs operating on spatial domains show superior performances compared to spectral ones, however their success is highly dependent on how the topology of input graphs is defined. In this paper, we introduce a novel framework for graph convolutional networks that learns the topological properties of graphs. The design principle of our method is based on the optimization of a constrained objective function which learns not only the usual convolutional parameters in GCNs but also a transformation basis that conveys the most relevant topological relationships in these graphs. Experiments conducted on the challenging task of skeleton-based action recognition shows the superiority of the proposed method compared to handcrafted graph design as well as the related work.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑