Teaching 3D geometry to deformable part models

@article{Pepik2012Teaching3G,
  title={Teaching 3D geometry to deformable part models},
  author={Bojan Pepik and Michael Stark and Peter V. Gehler and Bernt Schiele},
  journal={2012 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2012},
  pages={3362-3369}
}
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the detection of individual objects, higher-level applications such as 3D scene understanding or 3D object tracking would benefit from more fine-grained object hypotheses incorporating 3D geometric information, such as viewpoints or the locations of individual parts. In this paper, we help narrowing the representational gap… CONTINUE READING

Topics

Statistics

020402012201320142015201620172018
Citations per Year

212 Citations

Semantic Scholar estimates that this publication has 212 citations based on the available data.

See our FAQ for additional information.