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. |
Year | Venue | Field |
---|---|---|
2015 | ESANN | Computer science,Artificial intelligence,Artificial neural network,Machine learning |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniel Nascimento | 1 | 5 | 1.09 |
Rafael Lima de Carvalho | 2 | 3 | 1.44 |
Félix Mora-Camino | 3 | 41 | 12.11 |
Priscila M. V. Lima | 4 | 101 | 18.86 |
Felipe M. G. França | 5 | 249 | 51.12 |