Computational visual attention is a hot topic in computer vision. However, most efforts are devoted to model saliency, whilst the actual eye guidance problem, which brings into play the sequence of gaze shifts characterising overt attention, is overlooked. Further, in those cases where the generation of gaze behaviour is considered, stimuli of interest are by and large static (still images) rather than dynamic ones (videos). Under such circumstances, the work described in this note has a twofold aim: (i) addressing the problem of estimating and generating visual scan paths, that is the sequences of gaze shifts over videos; (ii) investigating the effectiveness in scan path generation offered by features dynamically learned on the base of human observers attention dynamics as opposed to bottom-up derived features. To such end a probabilistic model is proposed. By using a publicly available dataset, our approach is compared against a model of scan path simulation that does not rely on a learning step.
Worldly eyes on video: Learnt vs. reactive deployment of attention to dynamic stimuli / V. Cuculo, A. D'Amelio, G. Grossi, R. Lanzarotti (LECTURE NOTES IN ARTIFICIAL INTELLIGENCE). - In: Image Analysis and Processing – ICIAP 2019 / [a cura di] E. Ricci, S.Rota Bulò, C. Snoek, O. Lanz, S. Messelodi, N. Sebe. - [s.l] : Springer Verlag, 2019 Sep. - ISBN 9783030306410. - pp. 128-138 (( Intervento presentato al 20. convegno International Conference on Image Analysis and Processing, ICIAP 2019 tenutosi a Trento nel 2019 [10.1007/978-3-030-30642-7_12].
Worldly eyes on video: Learnt vs. reactive deployment of attention to dynamic stimuli
V. Cuculo
;A. D'Amelio;G. Grossi;R. Lanzarotti
2019
Abstract
Computational visual attention is a hot topic in computer vision. However, most efforts are devoted to model saliency, whilst the actual eye guidance problem, which brings into play the sequence of gaze shifts characterising overt attention, is overlooked. Further, in those cases where the generation of gaze behaviour is considered, stimuli of interest are by and large static (still images) rather than dynamic ones (videos). Under such circumstances, the work described in this note has a twofold aim: (i) addressing the problem of estimating and generating visual scan paths, that is the sequences of gaze shifts over videos; (ii) investigating the effectiveness in scan path generation offered by features dynamically learned on the base of human observers attention dynamics as opposed to bottom-up derived features. To such end a probabilistic model is proposed. By using a publicly available dataset, our approach is compared against a model of scan path simulation that does not rely on a learning step.File | Dimensione | Formato | |
---|---|---|---|
ICIAP2019_gaze_Scanpath_on_Videos.pdf
accesso riservato
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
4.31 MB
Formato
Adobe PDF
|
4.31 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Cuculo2019_Chapter_WorldlyEyesOnVideoLearntVsReac.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
1.73 MB
Formato
Adobe PDF
|
1.73 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.