Despite the popularity that saliency models have gained in the computer vision community, they are most often conceived, exploited and benchmarked without taking heed of a number of problems and subtle issues they bring about. When saliency maps are used as proxies for the likelihood of fixating a location in a viewed scene, one such issue is the temporal dimension of visual attention deployment. Through a simple simulation it is shown how neglecting this dimension leads to results that at best cast shadows on the predictive performance of a model and its assessment via benchmarking procedures.
Problems with Saliency Maps / G. Boccignone, V. Cuculo, A. D’Amelio (LECTURE NOTES IN ARTIFICIAL INTELLIGENCE). - In: Image Analysis and Processing – ICIAP 2019 / [a cura di] E. Ricci, S. Rota Bulo', C. Snoek, O.Lanz, S. Messelodi, N. Sebe. - Prima edizione. - [s.l] : Springer Nature, 2019 Sep. - ISBN 9783030306441. - pp. 35-46 (( Intervento presentato al 20. convegno International Conference on Image Analysis and Processing – ICIAP 2019 tenutosi a Trento nel 2019.
Titolo: | Problems with Saliency Maps |
Autori: | |
Parole Chiave: | Saliency model; Visual attention; Gaze deployment |
Settore Scientifico Disciplinare: | Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni Settore INF/01 - Informatica |
Data di pubblicazione: | set-2019 |
Digital Object Identifier (DOI): | http://dx.doi.org/10.1007/978-3-030-30645-8_4 |
Tipologia: | Book Part (author) |
Appare nelle tipologie: | 03 - Contributo in volume |
File in questo prodotto:
File | Descrizione | Tipologia | Licenza | |
---|---|---|---|---|
2019_ICIAP.pdf | Pre-print (manoscritto inviato all'editore) | Open Access Visualizza/Apri | ||
Boccignone2019_Chapter_ProblemsWithSaliencyMaps.pdf | Publisher's version/PDF | Administrator Richiedi una copia |