The INRIA-LIM-VocR and AXES submissions to Trecvid 2014 Multimedia Event Detection

Abstract : This paper describes our participation to the 2014 edition of the TrecVid Multimedia Event Detection task. Our system is based on a collection of local visual and audio descriptors, which are aggregated to global descriptors, one for each type of low-level descriptor, using Fisher vectors. Besides these features, we use two features based on convolutional networks: one for the visual channel, and one for the audio channel. Additional high-level featuresare extracted using ASR and OCR features. Finally, we used mid-level attribute features based on object and action detectors trained on external datasets. Our two submissions (INRIA-LIM-VocR and AXES) are identical interms of all the components, except for the ASR system that is used. We present an overview of the features andthe classification techniques, and experimentally evaluate our system on TrecVid MED 2011 data.
Type de document :
Autre publication
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger
Contributeur : Thoth Team <>
Soumis le : vendredi 20 février 2015 - 11:01:06
Dernière modification le : mercredi 11 avril 2018 - 01:58:15
Document(s) archivé(s) le : jeudi 21 mai 2015 - 11:40:43


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


  • HAL Id : hal-01089916, version 2



Matthijs Douze, Dan Oneata, Mattis Paulin, Clément Leray, Nicolas Chesneau, et al.. The INRIA-LIM-VocR and AXES submissions to Trecvid 2014 Multimedia Event Detection. 2014. 〈hal-01089916v2〉



Consultations de la notice


Téléchargements de fichiers