郑州大学学报(工学版)2026,Vol.47Issue(4):1-8,8.DOI:10.13705/j.issn.1671-6833.2026.04.011
基于扩散模型和交叉注意力机制的骨骼点动作识别方法
Diffusion Method and Cross-attention Mechanisms for Skeleton-based Action Recognition Method
摘要
Abstract
To address the problems of incomplete motion information caused by occlusion or missing joints in skele-ton-based action recognition,as well as the limited generalization ability of models with few-label conditions,a skeleton-based action recognition method DCMAE was proposed,which integrated a diffusion model with a cross-at-tention mechanism.Within a self-supervised learning framework,a spatio-temporal masking strategy was adopted,where the diffusion model learned the global distribution characteristics of motion sequences during the denoising process to improve classification accuracy under data-missing conditions.In the decoding stage,the cross-attention mechanism introduced encoder features to achieve spatio-temporal information interaction and guidance,thereby en-hancing the model's generalization ability in few-label conditions.Experiments conducted on the NTU RGB+D 60 and NTU RGB+D 120 datasets showed that the proposed method could achieve accuracy improvements of up to 14.9 percentage points and 3.0 percentage points,respectively,over SkeletonMAE with data-missing conditions and few-label conditions.The proposed method effectively enhanced the robustness of skeleton-based action recog-nition models to data-missing and few-label data,providing a new perspective for self-supervised action recognition research.关键词
骨骼点动作识别/自监督学习/掩蔽重建/扩散模型/交叉注意力机制Key words
skeleton-based action recognition/self-supervised learning/masked reconstruction/diffusion model/cross-attention mechanism分类
信息技术与安全科学引用本文复制引用
陈恩庆,李佳惠,郭新..基于扩散模型和交叉注意力机制的骨骼点动作识别方法[J].郑州大学学报(工学版),2026,47(4):1-8,8.基金项目
国家自然科学基金资助项目(62101503) (62101503)
河南省科技攻关计划项目(242102211017) (242102211017)