TUW @ Retrieving Diverse Social Images Task 2014
Type:
Speech with proceedings
Proceedings:
Working Notes Proceedings of the MediaEval 2014 Workshop
Publisher:
CEUR-WS
Pages:
ISBN:
ISSN: 1613-0073
Year:
2014
Abstract:
This paper describes the e orts of Vienna University of Technology (TUW) in the MediaEval 2014 Retrieving Diverse Social Images challenge. Our approach consisted of 3 steps: (1)<br> a pre-filtering based on Machine Learning, (2) a re-ranking<br> based on Word2Vec, and (3) a clustering part based on an<br> ensemble of clusters. Our best run reached a F@20 of 0.564.
TU Focus:
Information and Communication Technology
Reference:
J. Palotti, N. Rekabsaz, M. Lupu, A. Hanbury:
"TUW @ Retrieving Diverse Social Images Task 2014";
Vortrag: MediaEval Benchmarking Initiative for Multimedia Evaluation, Barcelona, ES; 16.10.2014 - 17.10.2014; in: "Working Notes Proceedings of the MediaEval 2014 Workshop", CEUR-WS, Vol-1263 (2014), ISSN: 1613-0073.
Zusätzliche Informationen
Last changed:
13.01.2015 17:31:36
TU Id:
235956
Accepted:
Accepted
Invited:
Department Focus:
Business Informatics
Info Link:
https://publik.tuwien.ac.at/showentry.php?ID=235956&lang=1
Abstract German: