Linking Names and Faces: Seeing the Problem in Different Ways

Abstract : In this paper we report on our experiments on linking names and faces as found in images and captions of online news websites. Whereas previously, the focus has been mostly on assigning names to the faces, we generalize this framework, exploiting the (a)symmetry between the visual and textual modalities. This leads to different schemes for assigning names to faces, assigning faces to names, and establishing name-face link pairs. On top of that, we investigate the use of textual and visual structural information to predict the presence of the corresponding entity in the other modality. This further improves the accuracy of the cross-media linking results.
Type de document :
Communication dans un congrès
Workshop on Faces in 'Real-Life' Images: Detection, Alignment, and Recognition, Oct 2008, Marseille, France. 2008
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00326731
Contributeur : Peter Sturm <>
Soumis le : dimanche 5 octobre 2008 - 13:04:01
Dernière modification le : lundi 6 octobre 2008 - 09:36:36
Document(s) archivé(s) le : lundi 8 octobre 2012 - 13:56:59

Fichier

Tuytelaa_eccv2008_final.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00326731, version 1

Collections

Citation

Phi The Pham, Marie-Francine Moens, Tinne Tuytelaars. Linking Names and Faces: Seeing the Problem in Different Ways. Workshop on Faces in 'Real-Life' Images: Detection, Alignment, and Recognition, Oct 2008, Marseille, France. 2008. 〈inria-00326731〉

Partager

Métriques

Consultations de la notice

123

Téléchargements de fichiers

61