Communication Dans Un Congrès Année : 2017

Multimodality and Deep Learning when predicting Media Interestingness

Résumé

This paper summarizes the computational models that Technicolor proposes to predict interestingness of images and videos within the MediaEval 2017 Predicting Media Interestingness Task. Our systems are based on deep learning architectures and exploit the use of both semantic and multimodal features. Based on the obtained results, we discuss our findings and obtain some scientific perspectives for the task.

Fichier principal
Vignette du fichier
Mediaeval_2017_paper_19.pdf (508.87 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-01585210 , version 1 (11-09-2017)

Licence

Identifiants

  • HAL Id : hal-01585210 , version 1

Citer

Eloïse Berson, Claire-Hélène Demarty, Ngoc Q K Duong. Multimodality and Deep Learning when predicting Media Interestingness. Proc. MediaEval 2017 Workshop, Sep 2017, Dublin, Ireland. ⟨hal-01585210⟩
169 Consultations
156 Téléchargements

Partager

  • More