Object, Scene and Actions
Date
2010-07-06
DOI
Authors
Ikizler-Cinbis, Nazli
Sclaroff, Stan
Version
OA Version
Citation
Ikizler-Cinbis, Nazli; Sclaroff, Stan. "Object, Scene and Actions", Technical Report BUCS-TR-2010-019, Computer Science Department, Boston University, July 6, 2010. [Available from: http://hdl.handle.net/2144/3796]
Abstract
In many cases, human actions can be identified not only by the singular observation of the human body in motion, but also properties of the surrounding scene and the related objects. In this paper, we look into this problem and propose an approach for human action recognition that integrates multiple feature channels from several entities such as objects, scenes and people. We formulate the problem in a multiple instance learning (MIL) framework, based on multiple feature channels. By using a discriminative approach, we join multiple feature channels embedded to the MIL space. Our experiments over the large YouTube dataset show that scene and object information can be used to complement person features for human action recognition.