• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Zhixuan, Wu (Zhixuan, Wu.) | Nan, Ma (Nan, Ma.) | Cheng, Wang (Cheng, Wang.) | Cheng, Xu (Cheng, Xu.) | Genbao, Xu (Genbao, Xu.) | Mingxing, Li (Mingxing, Li.)

Indexed by:

EI Scopus SCIE

Abstract:

For the problems of irrelevant frames and high model complexity in action recognition, we propose a Spatial- Temporal Hypergraph based on Dual -Stage Attention Network (STHG-DAN) for multi-view data lightweight action recognition. It includes two stages: Temporal Attention Mechanism based on Trainable Threshold (TAMTT) and Hypergraph Convolution based on Dynamic Spatial-Temporal Attention Mechanism (HG-DSTAM). In the first stage, TAM-TT uses a learning threshold to extract keyframes from multi-view videos, with the multiview data serving as a guarantee for providing more comprehensive information subsequently; In the second stage, HG-DSTAM divides the human joints into three parts: trunk, hand and leg to build spatial-temporal hypergraphs, extracts high -order features from spatial-temporal hypergraphs constructed of multi-view human body joints, inputs them into the dynamic spatial-temporal attention mechanism, and learns the intra frame correlation of multi-view data between the joint features of body parts, which can obtain the significant areas of action; We use multi-scale convolution operation and depth separable network, which can realize efficient action recognition with a few trainable parameters. We experiment on the NTU-RGB+D, NTU-RGB+D 120 and the imitating traffic police gesture dataset. The performance and accuracy of the model are better than the existing algorithms, effectively improving the machine and human body language interaction cognitive ability.

Keyword:

Action recognition Multi-view Dual-stage attention network Salient region Spatial-temporal hypergraph neural network

Author Community:

  • [ 1 ] [Zhixuan, Wu]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China
  • [ 2 ] [Cheng, Wang]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China
  • [ 3 ] [Cheng, Xu]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China
  • [ 4 ] [Mingxing, Li]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China
  • [ 5 ] [Nan, Ma]Beijing Univ Technol, Fac Informat & Technol, Beijing 100124, Peoples R China
  • [ 6 ] [Genbao, Xu]Beijing Univ Technol, Fac Informat & Technol, Beijing 100124, Peoples R China
  • [ 7 ] [Nan, Ma]Beijing Univ Technol, Engn Res Ctr Intelligence Percept & Autonomous Con, Minist Educ, Beijing 100124, Peoples R China
  • [ 8 ] [Genbao, Xu]Beijing Univ Technol, Engn Res Ctr Intelligence Percept & Autonomous Con, Minist Educ, Beijing 100124, Peoples R China

Reprint Author's Address:

  • [Nan, Ma]Beijing Univ Technol, Fac Informat & Technol, Beijing 100124, Peoples R China;;

Show more details

Related Keywords:

Source :

PATTERN RECOGNITION

ISSN: 0031-3203

Year: 2024

Volume: 151

8 . 0 0 0

JCR@2022

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count: 13

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:417/5316168
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.