Shallow Graph Convolutional Network for Skeleton-Based Action Recognition

Graph convolutional networks (GCNs) have brought considerable improvement to the skeleton-based action recognition task. Existing GCN-based methods usually use the fixed spatial graph size among all the layers. It severely affects the model's abilities to exploit the global and semantic discrim...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Sensors (Basel, Switzerland) Switzerland), 2021-01, Vol.21 (2), p.452
Hauptverfasser:	Yang, Wenjie, Zhang, Jianlin, Cai, Jingju, Xu, Zhiyong
Format:	Artikel
Sprache:	eng
Schlagworte:	activity recognition Apexes Bones Datasets graph convolution network Graph theory Humans Methods Neural networks Neural Networks, Computer Pattern Recognition, Automated Recognition Semantics Skeleton skeleton sequence
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!