Combining text/image in WikipediaMM task 2009 - Université Jean-Monnet-Saint-Étienne Access content directly
Conference Papers Year : 2009

Combining text/image in WikipediaMM task 2009

Christophe Moulin
  • Function : Author
  • PersonId : 854129
Cécile Barat
  • Function : Author
  • PersonId : 844844
Cédric Lemaître
  • Function : Author
  • PersonId : 864695
Mathias Géry
  • Function : Author
  • PersonId : 843869
Christophe Ducottet
Christine Largeron


This paper reports our multimedia information retrieval experiments carried out for the ImageCLEF track 2009. In 2008, we proposed a multimedia document model defined as a vector of textual and visual terms weighted using a tf.idf approch [5]. For our second participation, our goal was to improve this previous model in the following ways: 1) use of additional information for the textual part (legend and image bounding text extracted from the original documents, 2) use of different image detectors and descriptors, 3) new text / image combination approach. Results allow to evaluate the benefits of these different improvements.
Fichier principal
Vignette du fichier
moulin-paperCLEF2009.pdf (95.39 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

ujm-00432319 , version 1 (16-11-2009)


  • HAL Id : ujm-00432319 , version 1


Christophe Moulin, Cécile Barat, Cédric Lemaître, Mathias Géry, Christophe Ducottet, et al.. Combining text/image in WikipediaMM task 2009. ECDL 2009 - Workshop CLEF, Sep 2009, Corfu, Greece. ⟨ujm-00432319⟩
56 View
374 Download


Gmail Facebook X LinkedIn More