Local Feature Based Unsupervised Alignment of Object Class Images

@inproceedings{Lankinen2011LocalFB,
  title={Local Feature Based Unsupervised Alignment of Object Class Images},
  author={Jukka Lankinen and Joni-Kristian K{\"a}m{\"a}r{\"a}inen},
  booktitle={BMVC},
  year={2011}
}
Alignment of objects is a predominant problem in part-based methods for visual object categorisation (VOC). These methods should learn the parts and their spatial variation, which is difficult for objects in arbitrary poses. A straightforward solution is to annotate images with a set of “object landmarks”, but due to laborious manual annotation, semi-supervised methods requiring only a set of images and class labels are preferred. Recent state-of-the-art VOC methods utilise various approaches… CONTINUE READING
8 Citations
33 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 33 references

Spatial bag-of-features

  • Y. Cao, C. Wang, Z. Li, L. Zhang
  • In CVPR,
  • 2010
1 Excerpt

Similar Papers

Loading similar papers…