IRISA at TrecVid2015: Leveraging Multimodal LDA for Video Hyperlinking

Abstract : This paper presents the runs that we submitted in the context of the TRECVid 2015 Video Hyperlinking task. The task aims at proposing a set of video segments, called targets, to complement a query video segment defined as anchor. We used automatic transcripts and automatically extracted visual concept as input data. Two out of four runs use cross-modal LDA as a means to jointly make use of visual and audio information in the videos. As a contrast, one is based solely on visual information, and a combination of the cross-modal and visual runs is considered. After presenting the approaches, we discuss the performance obtained by the respective runs, as well as some of the limitations of the evaluation process.
Type de document :
Communication dans un congrès
TRECVid 2015 Workshop, Nov 2015, Gaithersburg, United States. TRECVid 2015 Workshop, Working Notes of the TRECVid 2015 Workshop
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01403726
Contributeur : Pascale Sébillot <>
Soumis le : dimanche 27 novembre 2016 - 14:11:49
Dernière modification le : samedi 18 février 2017 - 01:10:02
Document(s) archivé(s) le : mardi 21 mars 2017 - 10:06:22

Fichier

TRECVid_Workshop_paper_final.p...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01403726, version 1

Citation

Anca-Roxana Simon, Ronan Sicre, Rémi Bois, Guillaume Gravier, Pascale Sébillot. IRISA at TrecVid2015: Leveraging Multimodal LDA for Video Hyperlinking. TRECVid 2015 Workshop, Nov 2015, Gaithersburg, United States. TRECVid 2015 Workshop, Working Notes of the TRECVid 2015 Workshop. <hal-01403726>

Partager

Métriques

Consultations de
la notice

446

Téléchargements du document

33