TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation - Archive ouverte HAL Access content directly
Conference Papers Year : 2009

TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation

(1) , (1) , (1) , (1)
1
Thomas Mensink
  • Function : Author
  • PersonId : 853681
Jakob Verbeek
Cordelia Schmid
  • Function : Author
  • PersonId : 831154

Abstract

Image auto-annotation is an important open problem in computer vision. For this task we propose TagProp, a discriminatively trained nearest neighbor model. Tags of test images are predicted using a weighted nearest-neighbor model to exploit labeled training images. Neighbor weights are based on neighbor rank or distance. TagProp allows the integration of metric learning by directly maximizing the log-likelihood of the tag predictions in the training set. In this manner, we can optimally combine a collection of image similarity metrics that cover different aspects of image content, such as local shape descriptors, or global color histograms. We also introduce a word specific sigmoidal modulation of the weighted neighbor tag predictions to boost the recall of rare words. We investigate the performance of different variants of our model and compare to existing work. We present experimental results for three challenging data sets. On all three, TagProp makes a marked improvement as compared to the current state-of-the-art.
Vignette du fichier
GMVS.png (174.24 Ko) Télécharger le fichier Fichier principal
Vignette du fichier
GMVS09.pdf (239.37 Ko) Télécharger le fichier
Vignette du fichier
slides.pdf (2.15 Mo) Télécharger le fichier
Vignette du fichier
SupplMat.pdf (6.24 Mo) Télécharger le fichier
Format : Figure, Image
Origin : Files produced by the author(s)
Format : Other
Format : Other
Loading...

Dates and versions

inria-00439276 , version 1 (02-12-2010)

Identifiers

Cite

Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek, Cordelia Schmid. TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation. ICCV 2009 - 12th International Conference on Computer Vision, Sep 2009, Kyoto, Japan. pp.309-316, ⟨10.1109/ICCV.2009.5459266⟩. ⟨inria-00439276⟩
639 View
2932 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More