Workshop on Generic Object Recognition and Categorization
Abstract
We discuss the issues and challenges of generic object recognition. We argue that high-level, volumetric part-based descriptions are essential in the process of recognizing objects that might never have been observed before, and for which no exact geometric model is available. We discuss the representation scheme and its relationships to the three main tasks to solve: extracting descriptions from real images, under a wide variety of viewing conditions; learning new objects by storing their description in a database; recognizing objects by matching their description to that of similar previously observed objects.
Cite
Text
Dickinson et al. "Workshop on Generic Object Recognition and Categorization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2004. doi:10.1109/CVPR.2004.479Markdown
[Dickinson et al. "Workshop on Generic Object Recognition and Categorization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2004.](https://mlanthology.org/cvprw/2004/dickinson2004cvprw-workshop/) doi:10.1109/CVPR.2004.479BibTeX
@inproceedings{dickinson2004cvprw-workshop,
title = {{Workshop on Generic Object Recognition and Categorization}},
author = {Dickinson, Sven J. and Leonardis, Ales and Schiele, Bernt},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2004},
pages = {26},
doi = {10.1109/CVPR.2004.479},
url = {https://mlanthology.org/cvprw/2004/dickinson2004cvprw-workshop/}
}