3D RANs: 3D Residual Attention Networks for action recognition

In this work, we propose 3D Residual Attention Networks (3D RANs) for action recognition, which can learn spatiotemporal representation from videos. The proposed network consists of attention mechanism and 3D ResNets architecture, and it can capture spatiotemporal information in an end-to-end manner...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	The Visual computer 2020-06, Vol.36 (6), p.1261-1270
Hauptverfasser:	Cai, Jiahui, Hu, Jianguo
Format:	Artikel
Sprache:	eng
Schlagworte:	Activity recognition Artificial Intelligence Classification Computer Graphics Computer Science Feature maps Image Processing and Computer Vision Networks Neural networks Original Article Tensors
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!