Temporal Action Detection in Untrimmed Videos from Fine to Coarse Granularity

Temporal action detection in long, untrimmed videos is an important yet challenging task that requires not only recognizing the categories of actions in videos, but also localizing the start and end times of each action. Recent years, artificial neural networks, such as Convolutional Neural Network...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Applied sciences Jg. 8; H. 10; S. 1924
Hauptverfasser:	Yao, Guangle, Lei, Tao, Liu, Xianyuan, Jiang, Ping
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Basel MDPI AG 01.10.2018
Schlagworte:	action detection action proposal Artificial intelligence Classification convolutional neural network Localization Methods Neural networks Pattern recognition Proposals regression network Beijing China United States > US China
ISSN:	2076-3417, 2076-3417
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!