Visual event recognition in videos by learning from Web data

We propose a visual event recognition framework for consumer videos by leveraging a large amount of loosely labeled web videos (e.g., from YouTube). Observing that consumer videos generally contain large intraclass variations within the same type of events, we first propose a new method, called Alig...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 34(2012), 9 vom: 01. Sept., Seite 1667-80
1. Verfasser: Duan, Lixin (VerfasserIn)
Weitere Verfasser: Xu, Dong, Tsang, Ivor Wai-Hung, Luo, Jiebo
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2012
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't