文献类型：期刊文献

英文题名：Multi-View Time-Series Hypergraph Neural Network for Action Recognition

作者：Ma, Nan[1];Wu, Zhixuan[2];Feng, Yifan[3];Wang, Cheng[2];Gao, Yue[3]

第一作者：Ma, Nan

通讯作者：Gao, Y[1]

机构：[1]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China;[2]Beijing Union Univ, Coll Robot, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China;[3]Tsinghua Univ, Sch Software, BNRist, BLBCI,THUIBCS, Beijing 100084, Peoples R China

第一机构：Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

通讯机构：[1]corresponding author), Tsinghua Univ, Sch Software, BNRist, BLBCI,THUIBCS, Beijing 100084, Peoples R China.

年份：2024

卷号：33

起止页码：3301-3313

外文期刊名：IEEE TRANSACTIONS ON IMAGE PROCESSING

收录：;EI(收录号：20241916048446);Scopus(收录号：2-s2.0-85192198199);WOS:【SCI-EXPANDED(收录号:WOS:001218701100001)】；

基金：No Statement Available

语种：英文

外文关键词：Skeleton-based action recognition; spatial hypergraphs; temporal hypergraphs; representation learning; multi-view time-series hypergraph neural network

摘要：Recently, action recognition has attracted considerable attention in the field of computer vision. In dynamic circumstances and complicated backgrounds, there are some problems, such as object occlusion, insufficient light, and weak correlation of human body joints, resulting in skeleton-based human action recognition accuracy being very low. To address this issue, we propose a Multi-View Time-Series Hypergraph Neural Network (MV-TSHGNN) method. The framework is composed of two main parts: the construction of a multi-view time-series hypergraph structure and the learning process of multi-view time-series hypergraph convolutions. Specifically, given the multi-view video sequence frames, we first extract the joint features of actions from different views. Then, limb components and adjacent joints spatial hypergraphs based on the joints of different views at the same time are constructed respectively, temporal hypergraphs are constructed joints of the same view at continuous times, which are established high-order semantic relationships and cooperatively generate complementary action features. After that, we design a multi-view time-series hypergraph neural network to efficiently learn the features of spatial and temporal hypergraphs, and effectively improve the accuracy of skeleton-based action recognition. To evaluate the effectiveness and efficiency of MV-TSHGNN, we conduct experiments on NTU RGB+D, NTU RGB+D 120 and imitating traffic police gestures datasets. The experimental results indicate that our proposed method model achieves the new state-of-the-art performance.