Figure-ground segmentation improves handled object recognition in egocentric video

  title={Figure-ground segmentation improves handled object recognition in egocentric video},
  author={Xiaofeng Ren and Chunhui Gu},
  journal={2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
Identifying handled objects, i.e. objects being manipulated by a user, is essential for recognizing the person's activities. An egocentric camera as worn on the body enjoys many advantages such as having a natural first-person view and not needing to instrument the environment. It is also a challenging setting, where background clutter is known to be a major source of problems and is difficult to handle with the camera constantly and arbitrarily moving. In this work we develop a bottom-up… CONTINUE READING
Highly Influential
This paper has highly influenced 12 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 207 citations. REVIEW CITATIONS
113 Citations
29 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 113 extracted citations

207 Citations

Citations per Year
Semantic Scholar estimates that this publication has 207 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 29 references

Rehg . A scalable approach to activity recognition based on object use

  • J. Xiao, M. Shah
  • 2007

Similar Papers

Loading similar papers…