Please use this identifier to cite or link to this item:
Title: Unsupervised clustering of clickthrough data for automatic annotation of multimedia content
Authors: Tsapatsoulis, Nicolas 
Ntalianis, Klimis S. 
Doulamis, Anastasios D. 
Keywords: Computer science;Neural networks;Multimedia systems;Search engines;Cluster analysis;Back propagation (Artificial intelligence)
Category: Media and Communications
Field: Social Sciences
Issue Date: 2009
Publisher: Springer
Source: Artificial neural networks – ICANN 2009: 19th International Conference, Limassol, Cyprus, September 14-17, 2009, Proceedings, Part II, Pages 895-904
Abstract: Current low-level feature-based CBIR methods do not provide meaningful results on non-annotated content. On the other hand manual annotation is both time/money consuming and user-dependent. To address these problems in this paper we present an automatic annotation approach by clustering, in an unsupervised way, clickthrough data of search engines. In particular the query-log and the log of links the users clicked on are analyzed in order to extract and assign keywords to selected content. Content annotation is also accelerated by a carousel-like methodology. The proposed approach is feasible even for large sets of queries and features and theoretical results are verified in a controlled experiment, which shows that the method can effectively annotate multimedia files
ISBN: 978-3-642-04276-8 (print)
ISSN: 978-3-642-04277-5 (online)
DOI: 10.1007/978-3-642-04277-5_90
Rights: © Springer Berlin Heidelberg
Type: Book Chapter
Appears in Collections:Κεφάλαια βιβλίων/Book chapters

Show full item record

Citations 50

checked on Apr 28, 2018

Page view(s)

Last Week
Last month
checked on Aug 18, 2019

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.