 |
Conference papers
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.
Cited literature [6 references]
https://hal-enac.archives-ouvertes.fr/hal-01193153
Contributor : Laurence Porte <>
Submitted on : Monday, September 21, 2015 - 9:01:10 AM
Last modification on : Tuesday, October 20, 2020 - 10:32:04 AM
Long-term archiving on: : Monday, December 28, 2015 - 10:44:56 PM
Contributor : Laurence Porte <>
Submitted on : Monday, September 21, 2015 - 9:01:10 AM
Last modification on : Tuesday, October 20, 2020 - 10:32:04 AM
Long-term archiving on: : Monday, December 28, 2015 - 10:44:56 PM
File
es2015-26.pdf
Explicit agreement for this submission