Hierarchical Topic Models for Language-based Video Hyperlinking

Anca-Roxana Simon 1 Rémi Bois 1 Guillaume Gravier 1 Pascale Sébillot 1 Emmanuel Morin 2 Sien Moens 3
1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
LINA - Laboratoire d'Informatique de Nantes Atlantique
Abstract : We investigate video hyperlinking based on speech transcripts , leveraging a hierarchical topical structure to address two essential aspects of hyperlinking, namely, serendipity control and link justification. We propose and compare different approaches exploiting a hierarchy of topic models as an intermediate representation to compare the transcripts of video segments. These hierarchical representations offer a basis to characterize the hyperlinks, thanks to the knowledge of the topics who contributed to the creation of the links, and to control serendipity by choosing to give more weights to either general or specific topics. Experiments are performed on BBC videos from the Search and Hyperlinking task at MediaEval. Link precisions similar to those of direct text comparison are achieved however exhibiting different targets along with a potential control of serendipity.
Type de document :
Communication dans un congrès
Workshop on Speech, Language and Audio in Multimedia, 2015, Brisbane, Australia. <10.1145/2802558.2814642>
Liste complète des métadonnées

Contributeur : Guillaume Gravier <>
Soumis le : mercredi 2 septembre 2015 - 01:18:41
Dernière modification le : mercredi 2 août 2017 - 10:08:44
Document(s) archivé(s) le : mercredi 26 avril 2017 - 10:17:16


Fichiers produits par l'(les) auteur(s)



Anca-Roxana Simon, Rémi Bois, Guillaume Gravier, Pascale Sébillot, Emmanuel Morin, et al.. Hierarchical Topic Models for Language-based Video Hyperlinking. Workshop on Speech, Language and Audio in Multimedia, 2015, Brisbane, Australia. <10.1145/2802558.2814642>. <hal-01186429>



Consultations de
la notice


Téléchargements du document