Data-driven 3D Voxel Patterns for object category recognition

@article{Xiang2015Datadriven3V,
  title={Data-driven 3D Voxel Patterns for object category recognition},
  author={Yu Xiang and Wongun Choi and Yuanqing Lin and Silvio Savarese},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={1903-1911}
}
Despite the great progress achieved in recognizing objects as 2D bounding boxes in images, it is still very challenging to detect occluded objects and estimate the 3D properties of multiple objects from a single image. In this paper, we propose a novel object representation, 3D Voxel Pattern (3DVP), that jointly encodes the key properties of objects including appearance, 3D shape, viewpoint, occlusion and truncation. We discover 3DVPs in a data-driven way, and train a bank of specialized… CONTINUE READING
Highly Cited
This paper has 135 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 90 extracted citations

136 Citations

02040602015201620172018
Citations per Year
Semantic Scholar estimates that this publication has 136 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 39 references

Beyond pascal : A bench ­ mark for 3 d object detection in the wild

  • R. Mottaghi Y. Xiang, S. Savarese
  • WACV
  • 2014

Similar Papers

Loading similar papers…