Learning a Hierarchical Compositional Representation of Multiple Object Classes

Leonardis, Ales

doi:10.1109/CVPRW.2009.5204332

Learning a Hierarchical Compositional Representation of Multiple Object Classes

Ales Leonardis

CVPRW 2009 pp. 2

doi:10.1109/CVPRW.2009.5204332 /cvprw/2009/leonardis2009cvprw-learning/

Abstract

Visual categorization, recognition, and detection of objects has been an area of active research in the vision community for decades. Ultimately, the goal is to recognize and detect a large number of object classes in images within an acceptable time frame. This problem entangles three highly interconnected issues: the internal object representation which should expand sublinearly with the number of classes, means to learn the representation from a set of images, and an effective inference algorithm that matches the object representation against the representation produced from the scene.

CVPRW Semantic Scholar

Cite

Text

Leonardis. "Learning a Hierarchical Compositional Representation of Multiple Object Classes." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2009. doi:10.1109/CVPRW.2009.5204332

Markdown

[Leonardis. "Learning a Hierarchical Compositional Representation of Multiple Object Classes." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2009.](https://mlanthology.org/cvprw/2009/leonardis2009cvprw-learning/) doi:10.1109/CVPRW.2009.5204332

BibTeX

@inproceedings{leonardis2009cvprw-learning,
  title     = {{Learning a Hierarchical Compositional Representation of Multiple Object Classes}},
  author    = {Leonardis, Ales},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2009},
  pages     = {2},
  doi       = {10.1109/CVPRW.2009.5204332},
  url       = {https://mlanthology.org/cvprw/2009/leonardis2009cvprw-learning/}
}