One gaze is worth ten thousand (key-)words

Abstract : With the maturity of machine learning methods to provide satisfying Content-Based Image Retrieval systems (CBIR), research focus has recently turned back towards visual saliency analysis. The goal in these works is to extract even more efficient visual features than the existing ones. However, analyzing visual saliency is critically dependent on the task to be accomplished from the extracted visual features. A significant number of CBIR systems consider image retrieval as a binary classification problem: what is relevant for the user against what is irrelevant. In this paper, we focus on extracting relevant gaze features within the paradigm of visual preference in order to support the annotation by gaze for a CBIR system. We thus define a gaze acquisition protocol, design a benchmark from a subset of Pascal VOC database and present an in depth analysis of eye-tracking data for visual preference paradigm. Our paper provides new informations on relevant gaze features for image binary classification.
Type de document :
Communication dans un congrès
IEEE International Conference on Image Processing (ICIP), 2015, Sep 2015, Québec, Canada. pp.3150--3154 2015, IEEE International Conference on Image Processing (ICIP), 2015. <10.1109/ICIP.2015.7351384>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01323204
Contributeur : Diane Lingrand <>
Soumis le : lundi 30 mai 2016 - 11:32:00
Dernière modification le : jeudi 9 février 2017 - 16:58:52

Identifiants

Collections

UNICE | I3S | L3I

Citation

Stéphanie Lopez, Arnaud Revel, Diane Lingrand, Frédéric Precioso. One gaze is worth ten thousand (key-)words. IEEE International Conference on Image Processing (ICIP), 2015, Sep 2015, Québec, Canada. pp.3150--3154 2015, IEEE International Conference on Image Processing (ICIP), 2015. <10.1109/ICIP.2015.7351384>. <hal-01323204>

Partager

Métriques

Consultations de la notice

84