An Attention-Based Activity Recognition for Egocentric Video

@article{Matsuo2014AnAA,
  title={An Attention-Based Activity Recognition for Egocentric Video},
  author={Kenji Matsuo and Kentaro Yamada and Satoshi Ueno and Sei Naito},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  year={2014},
  pages={565-570}
}
In this paper, we propose a human activity recognition method from first-person videos, which provides a supplementary method to improve the recognition accuracy. Conventional methods detect objects and derive a user's behavior based on their taxonomy. One of the recent works has achieved accuracy improvement by determining key objects based on hand manipulation. However, such manipulation-based approach has a restriction on applicable scenes and object types because the user's hands don't… CONTINUE READING
Highly Cited
This paper has 56 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 33 extracted citations

57 Citations

010202015201620172018
Citations per Year
Semantic Scholar estimates that this publication has 57 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 36 references

, and J . Rehg . Understanding egocentric activities

  • N. Hofemann Hanheide, G. Sagerer
  • In ICCV
  • 2011

Similar Papers

Loading similar papers…