山西大学学报（自然科学版）2025，Vol.48Issue(1)：55-65,11.DOI:10.13451/j.sxu.ns.2024141
基于时空增强双分支图卷积网络的骨骼行为识别
Spatiotemporally Enhanced Dual-branch Graph Convolutional Network for Skeleton-based Action Recognition
摘要
Abstract
There are issues with existing graph convolution methods for skeleton-based action recognition,such as fixed joint seg-mentation,an emphasis on spatial information while neglecting temporal information,and a high number of network parameters.To address these issues,firstly,the information of symmetric joint is introduced to increase the interactive features of symmetric action.Secondly,the Multi-scale pyramid(MSP)time graph convolution module is added to form a Dual-branch(DB)network structure to improve the ability of the network to extract time dimension information.Finally,this study employs feature mapping and spatial ag-gregation(FM-SA)to filter out redundant parts in the weight matrix while preserving the original topological structure information,and incorporate a Squeeze-and-Excitation(SE)module to effectively enhance the extraction of spatial features and the expressive power of the feature maps.The experimental results show that compared with the benchmark model,the number of network parame-ters is reduced by 51％,the recognition accuracy of joint and bone flow on the NTU RGB+D 120 dataset is increased by 0.5％and 1.3％,and the fusion accuracy is increased by 0.7％and 0.5％.The recognition accuracy of NTU RGB+D and NW-UCLA datasets is increased by 0.1％,0.2％and 1.5％,respectively.The validity and feasibility of this model are verified.关键词
骨骼行为识别/关节分区/时空信息增强/多尺度金字塔/映射聚合Key words
skeleton behavior recognition/joint partitioning/spatiotemporal information enhancement/multi-scale pyramid/map-ping aggregation分类
数理科学引用本文复制引用
施宇航,何强,王恒友..基于时空增强双分支图卷积网络的骨骼行为识别[J].山西大学学报（自然科学版）,2025,48(1):55-65,11.基金项目
国家自然科学基金(62072024 （）
12301581) （）
北京市教育委员会科学研究计划项目(KM202210016002) （KM202210016002）
北京建筑大学硕士研究生创新项目(09081024002) （09081024002）
