We address the problem of object-based visual attention from a Bayesian standpoint. We contend with the issue of joint segmentation and saliency computation suitable to provide a sound basis for dealing with higher level information related to objects present in dynamic scene. To this end we propose a framework relying on nonparametric Bayesian techniques, namely variational inference on a mixture of Dirichlet processes.
Nonparametric Bayesian attentive video analysis / G. Boccignone - In: 2008 ICPR: 19th International Conference on Pattern RecognitionLos Alamitos : IEEE Computer Society Press, 2008 Dec 11. - ISBN 9781424421749. - pp. 1-4 (( Intervento presentato al 19. convegno International Conference on Pattern Recognition 2008 tenutosi a Tampa, Florida, USA nel 2008 [10.1109/ICPR.2008.4760948].
Nonparametric Bayesian attentive video analysis
G. BoccignonePrimo
2008
Abstract
We address the problem of object-based visual attention from a Bayesian standpoint. We contend with the issue of joint segmentation and saliency computation suitable to provide a sound basis for dealing with higher level information related to objects present in dynamic scene. To this end we propose a framework relying on nonparametric Bayesian techniques, namely variational inference on a mixture of Dirichlet processes.File | Dimensione | Formato | |
---|---|---|---|
ICPR08pre.pdf
accesso aperto
Tipologia:
Pre-print (manoscritto inviato all'editore)
Dimensione
738.47 kB
Formato
Adobe PDF
|
738.47 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.