Title | ||
---|---|---|
Unsupervised Clustering of Clickthrough Data for Automatic Annotation of Multimedia Content |
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. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-04277-5_90 | ICANN (2) |
Keywords | Field | DocType |
search engine,image retrieval | Annotation,Search engine,Automatic image annotation,Information retrieval,Computer science,Manual annotation,Image retrieval,Controlled experiment,Cluster analysis,Multimedia | Conference |
Volume | ISSN | Citations |
5769 | 0302-9743 | 1 |
PageRank | References | Authors |
0.35 | 13 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Klimis S. Ntalianis | 1 | 66 | 15.74 |
Anastasios D. Doulamis | 2 | 883 | 93.64 |
Nicolas Tsapatsoulis | 3 | 295 | 46.57 |
Nikolaos Doulamis | 4 | 691 | 80.72 |