ElderSim: A Synthetic Data Generation Platform for Human Action Recognition in Eldercare Applications

To train deep learning models for vision-based action recognition of elders' daily activities, we need large-scale activity datasets acquired under various daily living environments and conditions. However, most public datasets used in human action recognition either differ from or have limited...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-10
Hauptverfasser:	Hwang, Hochul, Jang, Cheongjae, Park, Geonwoo, Cho, Junghyun, Kim, Ig-Jae
Format:	Artikel
Sprache:	eng
Schlagworte:	Datasets Deep learning Human activity recognition Human motion Machine learning Synthetic data
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!