计算机与数字工程2023，Vol.51Issue(11)：2557-2562,6.DOI:10.3969/j.issn.1672-9722.2023.11.016
基于骨架的行为识别中图池化的应用
Application of Graph Pooling in Skeleton Based on Behavior Recognition
摘要
Abstract
Graph convolutional network(GCN)has been achieved excellent performance in skeleton-based action recognition tasks.However,not all the nodes are closely related to the action,and these irrelevant nodes must hinder the accuracy of recogni-tion.Therefore,graph pooling is applied to skeleton-based action recognition.Specifically,the feature is extracted by one graph convolutional layer,then the self-attention graph pooling is employed to remove irrelevant nodes,and finally the graph convolution-al layer is used for feature extraction and classification results are obtained.In this way,the network pays more attention to the nodes related to the action,while ignoring the influence of the irrelevant node information,and the recognition accuracy is corre-spondingly improved.The effectiveness of the method is verified on two large public datasets,NTU RGB-D and Kinetics skeleton.关键词
基于骨架的行为识别/图卷积/图池化/自注意力机制Key words
skeleton-based action recognition/graph convolutional network/graph pooling/attention mechanism分类
信息技术与安全科学引用本文复制引用
李卓,吴春雷..基于骨架的行为识别中图池化的应用[J].计算机与数字工程,2023,51(11):2557-2562,6.基金项目
山东省自然科学基金项目(编号:ZR2020MF136) （编号:ZR2020MF136）
山东省重点研发计划(编号:2019GGX101015) （编号:2019GGX101015）
中央高校基本科研业务费专项资金(编号:20CX05018A)资助. （编号:20CX05018A）
