The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs

@article{Cai2015TheCP,
  title={The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs},
  author={Hongping Cai and Qi Wu and Tadeo Corradi and Peter Hall},
  journal={ArXiv},
  year={2015},
  volume={abs/1505.00110}
}
The cross-depiction problem is that of recognising visual objects regardless of whether they are photographed, painted, drawn, etc. It is a potentially significant yet under-researched problem. Emulating the remarkable human ability to recognise objects in an astonishingly wide variety of depictive forms is likely to advance both the foundations and the applications of Computer Vision. In this paper we benchmark classification, domain adaptation, and deep learning methods; demonstrating that… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • It has been successful on conventional databases, and over a wide range of tasks, with recognition rates in excess of 90%.

Citations

Publications citing this paper.
SHOWING 1-10 OF 14 CITATIONS

Linking Art through Human Poses

Tomas Jenicek, Ondřej Chum
  • ArXiv
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND

Satellite Imagery Multiscale Rapid Detection with Windowed Networks

  • 2019 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2019
VIEW 3 EXCERPTS
CITES METHODS

Identifying Cross-Depicted Historical Motifs

  • 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR)
  • 2018
VIEW 1 EXCERPT
CITES BACKGROUND

Multiscale Rapid Detection with Windowed Networks

Adam Van Etten
  • 2018
VIEW 3 EXCERPTS
CITES METHODS

Who draw this? Caricaturist recognition using convolutional neural networks

  • 2018 26th Signal Processing and Communications Applications Conference (SIU)
  • 2018
VIEW 1 EXCERPT

References

Publications referenced by this paper.
SHOWING 1-10 OF 62 REFERENCES

Histograms of oriented gradients for human detection

  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 19 EXCERPTS
HIGHLY INFLUENTIAL

Distinctive Image Features from Scale-Invariant Keypoints

  • International Journal of Computer Vision
  • 2004
VIEW 19 EXCERPTS
HIGHLY INFLUENTIAL

Geodesic flow kernel for unsupervised domain adaptation

  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

Gradient field descriptor for sketch based retrieval and localization

  • 2010 IEEE International Conference on Image Processing
  • 2010
VIEW 15 EXCERPTS
HIGHLY INFLUENTIAL

Matching Local Self-Similarities across Images and Videos

  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
VIEW 17 EXCERPTS
HIGHLY INFLUENTIAL

Geometric blur for template matching

  • Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

In Search of Art

  • ECCV Workshops
  • 2014
VIEW 20 EXCERPTS
HIGHLY INFLUENTIAL