Virtual and Real World Adaptation for Pedestrian Detection

  title={Virtual and Real World Adaptation for Pedestrian Detection},
  author={David V{\'a}zquez and Antonio M. L{\'o}pez and Javier Mar{\'i}n and Daniel Ponsa and David Ger{\'o}nimo},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
Pedestrian detection is of paramount interest for many applications. Most promising detectors rely on discriminatively learnt classifiers, i.e., trained with annotated samples. However, the annotation step is a human intensive and subjective task worth to be minimized. By using virtual worlds we can automatically obtain precise and rich annotations. Thus, we face the question: can a pedestrian appearance model learnt in realistic virtual worlds work successfully for pedestrian detection in real… CONTINUE READING
Highly Cited
This paper has 114 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 79 extracted citations

114 Citations

Citations per Year
Semantic Scholar estimates that this publication has 114 citations based on the available data.

See our FAQ for additional information.


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

Frustratingly easy domain adaptation

  • III H.D.
  • Meeting of the Association for Computational…
  • 2007
Highly Influential
5 Excerpts

Similar Papers

Loading similar papers…