Spatio-Temporal Manifold Learning for Human Motions via Long-Horizon Modeling

Data-driven modeling of human motions is ubiquitous in computer graphics and computer vision applications, such as synthesizing realistic motions or recognizing actions. Recent research has shown that such problems can be approached by learning a natural motion manifold using deep learning on a larg...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on visualization and computer graphics. - 1996. - 27(2021), 1 vom: 22. Jan., Seite 216-227
1. Verfasser:	Wang, He (VerfasserIn)
Weitere Verfasser:	Ho, Edmond S L, Shum, Hubert P H, Zhu, Zhanxing
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2021
Zugriff auf das übergeordnete Werk:	IEEE transactions on visualization and computer graphics
Schlagworte:	Journal Article Research Support, Non-U.S. Gov't