Characterizing Humans on Riemannian Manifolds

  title={Characterizing Humans on Riemannian Manifolds},
  author={Diego Tosato and Mauro Spera and Marco Cristani and Vittorio Murino},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
In surveillance applications, head and body orientation of people is of primary importance for assessing many behavioral traits. Unfortunately, in this context people are often encoded by a few, noisy pixels so that their characterization is difficult. We face this issue, proposing a computational framework which is based on an expressive descriptor, the covariance of features. Covariances have been employed for pedestrian detection purposes, actually a binary classification problem on… CONTINUE READING
Highly Cited
This paper has 96 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 54 extracted citations

97 Citations

Citations per Year
Semantic Scholar estimates that this publication has 97 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 63 references

ARCO (Arrray of Covariance Matrices), Code and Data Sets

  • D. Tosato
  • 2013
Highly Influential
17 Excerpts

Riemannian Geometry: A Modern Introduction

  • I. Chavel
  • 2006
Highly Influential
3 Excerpts

CAVIAR Case Scenarios

  • R. Fisher
  • vision/CAVIAR…
  • 2013

ETHZ Data Set for Appearance-Based Modeling

  • W. R. Schwartz
  • 2013
2 Excerpts

Head Pose Image Database (Pointing ’04 ICPR Workshop)

  • N. Gourier
  • 2013
1 Excerpt

Similar Papers

Loading similar papers…