SRNet: Structured Relevance Feature Learning Network from Skeleton Data for Human Action Recognition

In recent years, human action recognition based on skeleton information has recently drawn increasing attention with published large-scale skeleton datasets. The most crucial factors for this task line in two aspects: the intra-frame representation for joint co-occurrences and the inter-frame repres...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE access 2019-01, Vol.7, p.1-1
Hauptverfasser:	Nie, Weizhi, Wang, Wei, Huang, Xiangdong
Format:	Artikel
Sprache:	eng
Schlagworte:	Convolution Convolutional Neural Network Correlation Data models Datasets Deep learning Feature extraction Human action recognition Human activity recognition Human motion Human skeleton information Joints (anatomy) Machine learning Mirrors Representations Skeleton Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!