Spatial–temporal hypergraph based on dual-stage attention network for multi-view data lightweight action recognition
Authors:
- Zhixuan WuZWZhixuan Wu
- Nan MaNMNan Ma
- Cheng WangCWCheng Wang
- Cheng XuCXCheng Xu
- Genbao XuGXGenbao Xu
- Mingxing LiMLMingxing Li
- 15 March 2024
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 151
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (61931012)
- Beijing Municipal Science and Technology Commission, Adminitrative Commission of Zhongguancun Science Park (Z221100000222016, S20210201107)
- Beijing Natural Science Foundation (4222025)
This publication has 39 references indexed in Scilit:
- MSA-GCN: Multiscale Adaptive Graph Convolution Network for gait emotion recognitionPattern Recognition, 2023
- Relation-mining self-attention network for skeleton-based human action recognitionPattern Recognition, 2023
- SpatioTemporal focus for skeleton-based action recognitionPattern Recognition, 2022
- Informed Patch Enhanced HyperGCN for skeleton-based action recognitionInformation Processing & Management, 2022
- Action Transformer: A self-attention model for short-time pose-based human action recognitionPattern Recognition, 2022
- Online learnable keyframe extraction in videos and its application with semantic word vector in action recognitionPattern Recognition, 2022
- Future vehicles: interactive wheeled robotsScience China Information Sciences, 2021
- Future vehicles: learnable wheeled robotsScience China Information Sciences, 2020
- Cascade multi-head attention networks for action recognitionComputer Vision and Image Understanding, 2020
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis2016