Why can't José read? - The problem of learning semantic associations in a robot environment

Abstract : We study the problem of learning to recognise objects in the context of autonomous agents. We cast object recognition as the process of attaching meaningful concepts to specific regions of an image. In other words, given a set of images and their captions, the goal is to segment the image, in either an intelligent or naive fashion, then to find the proper mapping between words and regions. In this paper, we demonstrate that a model that learns spatial relationships between individual words not only provides accurate annotations, but also allows one to perform recognition that respects the real-time constraints of an autonomous, mobile robot.
Keywords : LEAR
Type de document :
Communication dans un congrès
NAACL Human Language Technology Conference Workshop on Learning Word Meaning from Non-Linguistic Data, May 2003, Edmonton, Canada. The Association for Computational Linguistics (ACL), 2003, 〈http://clair.si.umich.edu/clair/anthology/query.cgi?type=Paper&id=W03-0608〉
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548236
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 08:42:10
Dernière modification le : jeudi 6 janvier 2011 - 16:30:01
Document(s) archivé(s) le : lundi 21 mars 2011 - 02:47:05

Fichier

CF03.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00548236, version 1

Citation

Peter Carbonetto, Nando De Freitas. Why can't José read? - The problem of learning semantic associations in a robot environment. NAACL Human Language Technology Conference Workshop on Learning Word Meaning from Non-Linguistic Data, May 2003, Edmonton, Canada. The Association for Computational Linguistics (ACL), 2003, 〈http://clair.si.umich.edu/clair/anthology/query.cgi?type=Paper&id=W03-0608〉. 〈inria-00548236〉

Partager

Métriques

Consultations de la notice

49

Téléchargements de fichiers

165