Audio-Visual Robot Command Recognition

Jordi Sanchez-Riera 1 Xavier Alameda-Pineda 1, * Radu Horaud 1, *
* Auteur correspondant
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : This paper addresses the problem of audio-visual command recognition in the framework of the D-META Grand Challenge. Temporal and non-temporal learning models are trained on visual and auditory descriptors. In order to set a proper baseline, the methods are tested on the ''Robot Gestures'' scenario of the publicly available RAVEL data set, following the leave-one-out cross-validation strategy. The classification-level audio-visual fusion strategy allows for compensating the errors of the unimodal (audio or vision) classifiers. The obtained results (an average audio-visual recognition rate of almost 80%) encourage us to investigate on how to further develop and improve the methodology described in this paper.
Type de document :
Communication dans un congrès
ICMI 2012 - 14th ACM International Conference on Multimodal Interaction, Oct 2012, Santa-Monica, CA, United States. ACM, pp.371-378, 2012, 〈http://dl.acm.org/citation.cfm?doid=2388676.2388760〉. 〈10.1145/2388676.2388760〉
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00768761
Contributeur : Team Perception <>
Soumis le : dimanche 23 décembre 2012 - 19:16:30
Dernière modification le : jeudi 11 janvier 2018 - 01:48:44
Document(s) archivé(s) le : dimanche 24 mars 2013 - 03:50:57

Fichier

gcp03-pineda.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Jordi Sanchez-Riera, Xavier Alameda-Pineda, Radu Horaud. Audio-Visual Robot Command Recognition. ICMI 2012 - 14th ACM International Conference on Multimodal Interaction, Oct 2012, Santa-Monica, CA, United States. ACM, pp.371-378, 2012, 〈http://dl.acm.org/citation.cfm?doid=2388676.2388760〉. 〈10.1145/2388676.2388760〉. 〈hal-00768761〉

Partager

Métriques

Consultations de la notice

309

Téléchargements de fichiers

145