Recognizing human actions by learning and matching shape-motion prototype trees

A shape-motion prototype-based approach is introduced for action recognition. The approach represents an action as a sequence of prototypes for efficient and flexible action matching in long video sequences. During training, an action prototype tree is learned in a joint shape and motion space via h...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - 34(2012), 3 vom: 26. März, Seite 533-47
1. Verfasser:	Jiang, Zhuolin (VerfasserIn)
Weitere Verfasser:	Lin, Zhe, Davis, Larry S
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 Research Support, U.S. Gov't, Non-P.H.S.