Object, Scene and Actions: Combining Multiple Features for Human Action Recognition

Ikizler-Cinbis N., Sclaroff S.

11th European Conference on Computer Vision, Heraklion, Yunanistan, 5 - 11 Eylül 2010, cilt.6311, ss.494-507 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 6311
  • Doi Numarası: 10.1007/978-3-642-15549-9_36
  • Basıldığı Şehir: Heraklion
  • Basıldığı Ülke: Yunanistan
  • Sayfa Sayıları: ss.494-507
  • Hacettepe Üniversitesi Adresli: Hayır

Özet

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 You Tube dataset show that scene and object information can be used to complement person features for human action recognition.