By and large, current visual attention models mostly rely, when considering static stimuli, on the following procedure. Given an image, a saliency map is computed, which, in turn, might serve the purpose of predicting a sequence of gaze shifts, namely a scanpath instantiating the dynamics of visual attention deployment. The temporal pattern of attention unfolding is thus confined to the scanpath generation stage, whilst salience is conceived as a static map, at best conflating a number of factors (bottom-up information, top-down, spatial biases, etc.). In this note we propose a novel sequential scheme that consists of a three-stage processing relying on a center-bias model, a context/layout model, and an object-based model, respectively. Each stage contributes, at different times, to the sequential sampling of the final scanpath. We compare the method against classic scanpath generation that exploits state-of-the-art static saliency model. Results show that accounting for the structure of the temporal unfolding leads to gaze dynamics close to human gaze behaviour.

How to look next? A data-driven approach for scanpath prediction / G. Boccignone, V. Cuculo, A. D'Amelio (LECTURE NOTES IN ARTIFICIAL INTELLIGENCE). - In: Formal Methods. FM 2019 International Workshops / [a cura di] E. Sekerinski, N. Moreira, J.N. Oliveira, D. Ratiu, R. Guidotti, M. Farrell, M. Luckcuck, D. Marmsoler, J. Campos, T. Astarte, L. Gonnord, A. Cerone, L. Couto, B. Dongol, P. Kutrib, D. Monteiro, D. Delmas. - Prima edizione. - [s.l] : Springer, 2020. - ISBN 9783030549930. - pp. 131-145 (( Intervento presentato al 3. convegno World Congress on Formal Methods tenutosi a Porto nel 2019.

How to look next? A data-driven approach for scanpath prediction

G. Boccignone;V. Cuculo
;
A. D'Amelio
2020

Abstract

By and large, current visual attention models mostly rely, when considering static stimuli, on the following procedure. Given an image, a saliency map is computed, which, in turn, might serve the purpose of predicting a sequence of gaze shifts, namely a scanpath instantiating the dynamics of visual attention deployment. The temporal pattern of attention unfolding is thus confined to the scanpath generation stage, whilst salience is conceived as a static map, at best conflating a number of factors (bottom-up information, top-down, spatial biases, etc.). In this note we propose a novel sequential scheme that consists of a three-stage processing relying on a center-bias model, a context/layout model, and an object-based model, respectively. Each stage contributes, at different times, to the sequential sampling of the final scanpath. We compare the method against classic scanpath generation that exploits state-of-the-art static saliency model. Results show that accounting for the structure of the temporal unfolding leads to gaze dynamics close to human gaze behaviour.
Gaze deployment; Saliency model; Scanpath prediction; Visual attention
Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni
Settore INF/01 - Informatica
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
2020_Datamod_Preprint.pdf

accesso aperto

Tipologia: Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione 9.87 MB
Formato Adobe PDF
9.87 MB Adobe PDF Visualizza/Apri
Boccignone2020_Chapter_HowToLookNextAData-DrivenAppro.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 6.72 MB
Formato Adobe PDF
6.72 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2434/760600
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact