Constrained Dominant sets and Its applications in computer vision
Computer Vision and Pattern Recognition
2020-02-17 v1
Abstract
In this thesis, we present new schemes which leverage a constrained clustering method to solve several computer vision tasks ranging from image retrieval, image segmentation and co-segmentation, to person re-identification. In the last decades clustering methods have played a vital role in computer vision applications; herein, we focus on the extension, reformulation, and integration of a well-known graph and game theoretic clustering method known as Dominant Sets. Thus, we have demonstrated the validity of the proposed methods with extensive experiments which are conducted on several benchmark datasets.
Cite
@article{arxiv.2002.06028,
title = {Constrained Dominant sets and Its applications in computer vision},
author = {Alemu Leulseged Tesfaye},
journal= {arXiv preprint arXiv:2002.06028},
year = {2020}
}
Comments
PhD dissertation. arXiv admin note: substantial text overlap with arXiv:1608.00641 by other authors