Rapport (Rapport De Recherche) Année : 2008

Rate versus synchrony code for human action recognition

Résumé

We propose a bio-inspired feedforward spiking network modeling two brain areas dedicated to motion (V1 and MT), and we show how the spiking output can be exploited in a computer vision application: action recognition. In order to analyze spike trains, we consider two characteristics of the neural code: mean firing rate of each neuron and synchrony between neurons. Interestingly, we show that they carry some relevant information for the action recognition application. We compare our results to Jhuang et al. (2007) on the Weizmann database. As a conclusion, we are convinced that spiking networks represent a powerful alternative framework for real vision applications that will benefit from recent advances in computational neuroscience

Fichier principal
Vignette du fichier
RR-6669.pdf (1.94 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

inria-00326588 , version 1 (03-10-2008)

Licence

Identifiants

  • HAL Id : inria-00326588 , version 1

Citer

Maria-Jose Escobar, G. Masson, Thierry Viéville, Pierre Kornprobst. Rate versus synchrony code for human action recognition. [Research Report] RR-6669, INRIA. 2008, pp.36. ⟨inria-00326588⟩
421 Consultations
699 Téléchargements

Partager

  • More