Linking Names and Faces: Seeing the Problem in Different Ways - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

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.
Fichier principal
Vignette du fichier
Tuytelaa_eccv2008_final.pdf (352.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00326731 , version 1 (05-10-2008)

Identifiers

  • HAL Id : inria-00326731 , version 1

Cite

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, Erik Learned-Miller and Andras Ferencz and Frédéric Jurie, Oct 2008, Marseille, France. ⟨inria-00326731⟩

Collections

REALFACES2008
87 View
42 Download

Share

Gmail Facebook X LinkedIn More