BriefGPT.xyz
Sep, 2018
基于部分特征的图卷积神经网络用于动作识别
Part-based Graph Convolutional Network for Action Recognition
HTML
PDF
Kalpit Thakkar, P J Narayanan
TL;DR
本文提出了一种基于部件图卷积网络的人体动作识别模型,该模型将骨骼图分为四个子图,并使用相对坐标和时间位移代替3D关节点特征,相对于使用整个骨骼图的模型,能够提高识别性能,实现了对挑战性基准数据集NTURGB+D和HDM05的骨骼动作识别的最先进水平。
Abstract
human actions
comprise of joint motion of articulated body parts or `gestures'. Human skeleton is intuitively represented as a sparse graph with joints as nodes and natural connections between them as edges.
graph convo
→