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

  title={Object, Scene and Actions: Combining Multiple Features for Human Action Recognition},
  author={Nazli Ikizler-Cinbis and Stan Sclaroff},
In many cases, human actions can be identified not only by the s ingular observation of the human body in motion, but also propert ies 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 integ rat s multiple feature channels from several entities such as objects, scenes and p eople. We formulate the problem in a multiple instance learning (MIL) framework , based on multiple feature channels. By… CONTINUE READING
Highly Influential
This paper has highly influenced 15 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 285 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 182 extracted citations

286 Citations

Citations per Year
Semantic Scholar estimates that this publication has 286 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 32 references

Similar Papers

Loading similar papers…