MRIM-LIG at ImageCLEF 2016 Scalable Concept Image Annotation Task - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

MRIM-LIG at ImageCLEF 2016 Scalable Concept Image Annotation Task

Résumé

This paper describes the participation of the the MRIM research Group of the LIG laboratory in the ImageCLEF scalable concept image annotation subtask 1. We made use of a classical framework to annotate the 500K images of this task: we tuned an existing Convolutional Neural Network model to learn the 251 concepts and to locate bounding boxes of such concepts, and we applied a specific process to handle faces and face parts. Because of time constraints, we fully processed 35% of the full corpus (i.e. 180K images), and partially the remaining images of the corpus. For our first participation to this task, the results obtained show that we have to manage the localization in a more effective way.
Fichier principal
Vignette du fichier
LIfelog_MRIM-2016.pdf (231.96 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01572645 , version 1 (08-08-2017)

Identifiants

  • HAL Id : hal-01572645 , version 1

Citer

Maxime Portaz, Mateusz Budnik, Philippe Mulhem, Johann Poignant. MRIM-LIG at ImageCLEF 2016 Scalable Concept Image Annotation Task. Clef 2016 Conference, Sep 2016, Evora, Portugal. pp.363-370. ⟨hal-01572645⟩
49 Consultations
36 Téléchargements

Partager

Gmail Facebook X LinkedIn More