IRISA at TrecVid2015: Leveraging Multimodal LDA for Video Hyperlinking - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

IRISA at TrecVid2015: Leveraging Multimodal LDA for Video Hyperlinking

Résumé

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.
Fichier principal
Vignette du fichier
TRECVid_Workshop_paper_final.pdf (308.88 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01403726 , version 1 (27-11-2016)

Identifiants

  • HAL Id : hal-01403726 , version 1

Citer

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. ⟨hal-01403726⟩
362 Consultations
96 Téléchargements

Partager

Gmail Facebook X LinkedIn More