DMCA
An experimental comparison of similarity adaptation approaches (2011)
| Venue: | In Proc. of AMR’11 |
| Citations: | 6 - 3 self |
BibTeX
@INPROCEEDINGS{Stober11anexperimental,
author = {Sebastian Stober and Andreas Nürnberger},
title = {An experimental comparison of similarity adaptation approaches},
booktitle = {In Proc. of AMR’11},
year = {2011}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. Similarity plays an important role in many multimedia retrieval applications. However, it often has many facets and its perception is highly subjective – very much depending on a person’s background or retrieval goal. In previous work, we have developed various approaches for modeling and learning individual distance measures as a weighted linear combination of multiple facets in different application scenarios. Based on a generalized view of these approaches as an optimization problem guided by generic relative distance constraints, we describe ways to address the problem of constraint violations and finally compare the different approaches against each other. To this end, a comprehensive experiment using the Magnatagatune benchmark dataset is conducted. 1
Keyphrases
experimental comparison similarity adaptation approach retrieval goal constraint violation optimization problem different application scenario many facet previous work generalized view magnatagatune benchmark dataset many multimedia retrieval application generic relative distance constraint comprehensive experiment multiple facet important role person background different approach weighted linear combination various approach individual distance measure
