Automatic propagation of manual annotations for multimodal person identification in TV shows - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Automatic propagation of manual annotations for multimodal person identification in TV shows

Résumé

In this paper an approach to human annotation propagation for person identification in the multimodal context is proposed. A system is used, which combines speaker diarization and face clustering to produce multimodal clusters. The whole multimodal clusters are later annotated rather than just single tracks, which is done by propagation. Optical character recogni- tion systems provides initial annotation. Four different strategies, which select candidates for annotation, are tested. The initial results of annotation propagation are promising. With the use of a proper active learning selection strategy the human annotator involvement could be reduced even further.
Fichier principal
Vignette du fichier
draft.pdf (336.32 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01002927 , version 1 (07-06-2014)

Identifiants

  • HAL Id : hal-01002927 , version 1

Citer

Mateusz Budnik, Johann Poignant, Laurent Besacier, Georges Quénot. Automatic propagation of manual annotations for multimodal person identification in TV shows. 12th International Workshop on Content-Based Multimedia Indexing (CBMI), Jun 2014, Klagenfurt, Austria. ⟨hal-01002927⟩
168 Consultations
2145 Téléchargements

Partager

Gmail Facebook X LinkedIn More