A WiSARD-based multi-term memory framework for online tracking of objects

Abstract : In this paper it is proposed a generic object tracker with real- time performance. The proposed tracker is inspired on the hierarchical short-term and medium-term memories for which patterns are stored as discriminators of a WiSARD weightless neural network. This approach is evaluated through benchmark video sequences published by Babenko et al. Experiments show that the WiSARD-based approach outperforms most of the previous results in the literature, with respect to the same dataset.
Type de document :
Communication dans un congrès
ESANN 2015, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2015, Bruges, Belgium. pp.978-287587014-8, 〈10.13140/RG.2.1.3387.5687〉
Liste complète des métadonnées

Littérature citée [6 références]  Voir  Masquer  Télécharger

https://hal-enac.archives-ouvertes.fr/hal-01193153
Contributeur : Laurence Porte <>
Soumis le : lundi 21 septembre 2015 - 09:01:10
Dernière modification le : lundi 21 mars 2016 - 17:43:42
Document(s) archivé(s) le : lundi 28 décembre 2015 - 22:44:56

Fichier

es2015-26.pdf
Accord explicite pour ce dépôt

Identifiants

Collections

Citation

Daniel Do Nascimiento, Rafael Lima de Carvalho, Felix Antonio Claudio Mora-Camino, Priscila V. M. Lima, Felipe Franca. A WiSARD-based multi-term memory framework for online tracking of objects. ESANN 2015, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2015, Bruges, Belgium. pp.978-287587014-8, 〈10.13140/RG.2.1.3387.5687〉. 〈hal-01193153〉

Partager

Métriques

Consultations de la notice

108

Téléchargements de fichiers

92