Fusion of Speech, Faces and Text for Person Identification in TV Broadcast - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Fusion of Speech, Faces and Text for Person Identification in TV Broadcast

Jakob Verbeek

Résumé

The REPERE challenge is a project aiming at the evaluation of systems for supervised and unsupervised multimodal recognition of people in TV broadcast. In this paper, we describe, evaluate and discuss QCompere consortium submissions to the 2012 REPERE evaluation campaign dry-run. Speaker identification (and face recognition) can be greatly improved when combined with name detection through video optical character recognition. Moreover, we show that unsupervised multimodal person recognition systems can achieve performance nearly as good as supervised monomodal ones (with several hundreds of identity models).
Fichier principal
Vignette du fichier
bredin12eccvws.pdf (798.74 Ko) Télécharger le fichier
Vignette du fichier
Screenshot.png (129.64 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Format : Figure, Image
Loading...

Dates et versions

hal-00722884 , version 1 (06-08-2012)

Identifiants

Citer

Hervé Bredin, Johann Poignant, Makarand Tapaswi, Guillaume Fortier, Viet Bac Le, et al.. Fusion of Speech, Faces and Text for Person Identification in TV Broadcast. ECCV 2012 - 12th European Conference on Computer Vision, Oct 2012, Firenze, Italy. pp.385-394, ⟨10.1007/978-3-642-33885-4_39⟩. ⟨hal-00722884⟩
998 Consultations
685 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More