We discuss how gaze behavior of an observer can be simulated as a Monte Carlo sampling of a distribution obtained from the saliency map of the observed image. To such end we propose the Levy Hybrid Monte Carlo algorithm, a dynamic Monte Carlo method in which the walk on the distribution landscape is modelled through Levy flights. Some preliminary results are presented comparing with data gathered by eye-tracking human observers involved in an emotion recognition task from facial expression displays.
Gaze Shifts as Dynamical Random Sampling / G. Boccignone, M. Ferraro - In: 2010 2nd european workshop on visual information processing (EUVIP) : Paris, 5-7 July 2010, Telecom ParisTech Paris, FranceLos Alamitos : EEE Computer Society, 2010. - ISBN 9781424472888. - pp. 29-34 (( Intervento presentato al 2. convegno European Workshop on Visual Information Processing tenutosi a Paris nel 2010 [10.1109/EUVIP.2010.5699099].
Gaze Shifts as Dynamical Random Sampling
G. BoccignonePrimo
;
2010
Abstract
We discuss how gaze behavior of an observer can be simulated as a Monte Carlo sampling of a distribution obtained from the saliency map of the observed image. To such end we propose the Levy Hybrid Monte Carlo algorithm, a dynamic Monte Carlo method in which the walk on the distribution landscape is modelled through Levy flights. Some preliminary results are presented comparing with data gathered by eye-tracking human observers involved in an emotion recognition task from facial expression displays.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
