Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

The joint submission of the TU Berlin and Fraunhofer FIRST (TUBFI) to the image CLEF 2011 photo annotation task

 
: Binder, A.; Samek, W.; Kloft, M.; Müller, C.; Müller, K.-R.; Kawanabe, M.

:
Fulltext ()

Petras, V.:
CLEF 2011 Working Notes. Online resource : Conference on Multilingual and Multimodal Information Access Evaluation, Amsterdam, The Netherlands, September 19-22, 2011
Amsterdam, 2011 (CEUR Workshop Proceedings 1177)
http://ceur-ws.org/Vol-1177/
9 pp.
Conference on Multilingual and Multimodal Information Access Evaluation (CLEF) <2011, Amsterdam>
English
Conference Paper, Electronic Publication
Fraunhofer FIRST ()

Abstract
In this paper we present details on the joint submission of TU Berlin and Fraunhofer FIRST to the ImageCLEF 2011 Photo Annotation Task.We sought to experiment with extensions of Bag-of-Words (BoW) models at several levels and to apply several kernel-based learning methods recently developed in our group. For classifier training we used non-sparse multiple kernel learning (MKL) and an efficient multi-task learning (MTL) heuristic based on MKL over kernels from classifier outputs. For the multi-modal fusion we used a smoothing method on tag-based features inspired by Bag-of-Words soft mappings and Markov random walks. We submitted one multi-modal run extended by the user tags and four purely visual runs based on Bag-of-Words models. Our best visual result which used the MTL method was ranked first according to mean average precision (MAP) within the purely visual submissions. Our multi-modal submission achieved the first rank by MAP among the multi-modal submissions and t he best MAP among all submissions. Submissions by other groups such as BPACAD, CAEN, UvA-ISIS, LIRIS were ranked closely.

: http://publica.fraunhofer.de/documents/N-439305.html