Conditional models for contextual human motion recognition

  title={Conditional models for contextual human motion recognition},
  author={Cristian Sminchisescu and Atul Kanaujia and Dimitris N. Metaxas},
  journal={Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1},
  pages={1808-1815 Vol. 2}
We present algorithms for recognizing human motion in monocular video sequences, based on discriminative conditional random field (CRF) and maximum entropy Markov models (MEMM). Existing approaches to this problem typically use generative (joint) structures like the hidden Markov model (HMM). Therefore they have to make simplifying, often unrealistic assumptions on the conditional independence of observations given the motion class labels and cannot accommodate overlapping features or long term… CONTINUE READING
Highly Influential
This paper has highly influenced 22 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 456 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 301 extracted citations

456 Citations

Citations per Year
Semantic Scholar estimates that this publication has 456 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 41 references

Conditional models for contextual human motion recognition

  • C. Sminchisescu, A. Kanaujia, Z. Li, D. Metaxas
  • in: IEEE International Conference on Computer…
  • 2005

Similar Papers

Loading similar papers…