A Hybrid Approach for Retrieving Diverse Social Images of Landmarks

TitleA Hybrid Approach for Retrieving Diverse Social Images of Landmarks
Publication TypeConference Paper
Year of Publication2015
AuthorsDang-Nguyen, D-T, Piras, L, Giacinto, G, Boato, G, De Natale, FGB
Conference NameIEEE International Conference on Multimedia & Expo (ICME)
Date Published07/2015
Conference LocationTorino
Keywordscbir00, image categorization

In this paper, we present a novel method that can produce a visual description of a landmark by choosing the most diverse pictures that best describe all the details of the queried location from community-contributed datasets. The main idea of this method is to filter out non-relevant images at a first stage and then cluster the images according to textual descriptors first, and then to visual descriptors. The extraction of images from different clusters according to a measure of user's credibility, allows obtaining a reliable set of diverse and relevant images. Experimental results performed on the MediaEval 2014 ``Retrieving Diverse Social Images" dataset show that the proposed approach can achieve very good performance outperforming state-of-art techniques.

Citation Key1211
ICME2015_printed.pdf1.16 MB