A WiSARD-based multi-term memory framework for online tracking of objects - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année :

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

(1) , (2, 1) , (2) , (3) , (1)
1
2
3

Résumé

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.
Fichier principal
Vignette du fichier
es2015-26.pdf (1.59 Mo) Télécharger le fichier
Origine : Accord explicite pour ce dépôt
Loading...

Dates et versions

hal-01193153 , version 1 (21-09-2015)

Identifiants

Citer

Daniel N Do Nascimiento, Rafael Lima de Carvalho, Felix Mora-Camino, Priscila V. M. Lima, Felipe M G 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⟩
91 Consultations
112 Téléchargements

Altmetric

Partager

Gmail Facebook Twitter LinkedIn More