T[sub.ohjm]-Trained Multiscale Spatial Temporal Graph Convolutional Neural Network for Semi-Supervised Skeletal Action Recognition

In recent years, spatial-temporal graph convolutional networks have played an increasingly important role in skeleton-based human action recognition. However, there are still three major limitations to most ST-GCN-based approaches: (1) They only use a single joint scale to extract action features, o...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Electronics (Basel) 2022, Vol.11 (21)
Hauptverfasser: Gou, Ruru, Yang, Wenzhu, Luo, Zifei, Yuan, Yunfeng, Li, Andong
Format: Report
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!