Human Motion Prediction via Dual-Attention and Multi-Granularity Temporal Convolutional Networks
Sensors · 2023
DOI: 10.3390/s23125653 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Biaozhang Huang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory Measurement and Control of CSE Ministry of Education, School of Automation, Southeast University, Nanjing 210002, China. Hauptthemen laut MEDLINE: Quality of Life, Algorithms. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Projects of Key R&D Program of Jiangsu Province, Shenzhen Natural Science Foundation Grant.
Abstract (Originalsprache)
Intelligent devices, which significantly improve the quality of life and work efficiency, are now widely integrated into people’s daily lives and work. A precise understanding and analysis of human motion is essential for achieving harmonious coexistence and efficient interaction between intelligent devices and humans. However, existing human motion prediction methods often fail to fully exploit the dynamic spatial correlations and temporal dependencies inherent in motion sequence data, which leads to unsatisfactory prediction results. To address this issue, we proposed a novel human motion prediction method that utilizes dual-attention and multi-granularity temporal convolutional networks (DA-MgTCNs). Firstly, we designed a unique dual-attention (DA) model that combines joint attention and channel attention to extract spatial features from both joint and 3D coordinate dimensions. Next, we designed a multi-granularity temporal convolutional networks (MgTCNs) model with varying receptive fields to flexibly capture complex temporal dependencies. Finally, the experimental results from two benchmark datasets, Human3.6M and CMU-Mocap, demonstrated that our proposed method significantly outperformed other methods in both short-term and long-term prediction, thereby verifying the effectiveness of our algorithm.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory Measurement and Control of CSE Ministry of Education, School of Automation, Southeast University, Nanjing 210002, China.
- Nanjing Center for Applied Mathematics, Nanjing 211135, China.
Förderung
- National Natural Science Foundation of China
- Key Projects of Key R&D Program of Jiangsu Province
- Shenzhen Natural Science Foundation Grant
- Key Projects of the Key R&D Program of Jiangsu Province
- Shenzhen Natural Science Foundation
Zitieren
APA
Huang, B., & Li, X. (2023). Human Motion Prediction via Dual-Attention and Multi-Granularity Temporal Convolutional Networks. Sensors. https://doi.org/10.3390/s23125653
Vancouver
Huang B, Li X. Human Motion Prediction via Dual-Attention and Multi-Granularity Temporal Convolutional Networks. Sensors. 2023. doi:10.3390/s23125653
BibTeX
@article{Huang2023,
author = {Huang, Biaozhang and Li, Xinde},
title = {Human Motion Prediction via Dual-Attention and Multi-Granularity Temporal Convolutional Networks},
journal = {Sensors},
year = {2023},
doi = {10.3390/s23125653}
}
EUVIMED