Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.11851/1972| Title: | Generalized Class Representative Computation with Graph Embedding and Clustering | Other Titles: | Genelleştirilmiş Çizge Gömme ve Öbekleme İle Sınıf Temsilcisi Çıkarma | Authors: | Aydos, Fahri Demirci, Muhammed Fatih |
Keywords: | class representative object recognition graph embedding clustering |
Publisher: | IEEE | Source: | Aydos, F., & Demirci, M. F. (2015, May). Generalized class representative computation with graph embedding and clustering. In 2015 23nd Signal Processing and Communications Applications Conference (SIU) (pp. 2525-2528). IEEE. | Abstract: | In this paper, we propose an object category representation framework by first showing objects as graph structures and embedding graphs into vector spaces for color object recognition. The object categories are then built by clustering. The distance between an object and an object category is computed by Earth Mover's Distance. The proposed method has been successfully evaluated on a number of datasets, and its performance has been computed against previous techniques. | Description: | 23nd Signal Processing and Communications Applications Conference (SIU) (2015 : Malatya, TURKEY) | URI: | https://ieeexplore.ieee.org/document/7130398 https://hdl.handle.net/20.500.11851/1972 |
ISBN: | 978-1-4673-7386-9 | ISSN: | 2165-0608 |
| Appears in Collections: | Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection |
Show full item record
CORE Recommender
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.