Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion

@inproceedings{Zhu2008UnsupervisedSL,
  title={Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion},
  author={Long Zhu and Chenxi Lin and Haoda Huang and Yuanhao Chen and Alan L. Yuille},
  booktitle={ECCV},
  year={2008}
}
We describe a new method for unsupervised structure learning of a hierarchical compositional model (HCM) for deformable objects. The learning is unsupervised in the sense that we are given a training dataset of images containing the object in cluttered backgrounds but we do not know the position or boundary of the object. The structure learning is performed by a bottom-up and top-down process. The bottom-up process is a novel form of hierarchical clustering which recursively composes proposals… CONTINUE READING
Highly Cited
This paper has 189 citations. REVIEW CITATIONS
73 Citations
21 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 73 extracted citations

190 Citations

02040'09'11'13'15'17
Citations per Year
Semantic Scholar estimates that this publication has 190 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 21 references

Similar Papers

Loading similar papers…