doi:10.1016/j.cag.2024.103983engMartín, DanielGutiérrez, DiegoMasia, BeléntSPM-Net: A probabilistic spatio-temporal approach for scanpath predictionART-2024-139083Predicting the path followed by the viewer’s eyes when observing an image (a scanpath) is a challenging problem, particularly due to the inter- and intra-observer variability and the spatio-temporal dependencies of the visual attention process. Most existing approaches have focused on progressively optimizing the prediction of a gaze point given the previous ones. In this work we propose instead a probabilistic approach, which we call tSPM-Net. We build our method to account for observers’ variability by resorting to Bayesian deep learning and a probabilistic approach. Besides, we optimize our model to jointly consider both spatial and temporal dimensions of scanpaths using a novel spatio-temporal loss function based on a combination of Kullback–Leibler divergence and dynamic time warping. Our tSPM-Net yields results that outperform those of current state-of-the-art approaches, and are closer to the human baseline, suggesting that our model is able to generate scanpaths whose behavior closely resembles those of the real ones.2024http://zaguan.unizar.es/record/13620110.1016/j.cag.2024.103983http://zaguan.unizar.es/record/136201oai:zaguan.unizar.es:136201info:eu-repo/grantAgreement/ES/AEI/PID2022-141539NB-I00info:eu-repo/grantAgreement/ES/DGA/T34-20Rinfo:eu-repo/grantAgreement/EC/H2020/956585/EU/Predictive Rendering In Manufacture and Engineering/PRIMEThis project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 956585-PRIMECOMPUTERS & GRAPHICS-UK 122 (2024), 103983 [9 pp.]by-nchttps://creativecommons.org/licenses/by-nc/4.0/deed.esinfo:eu-repo/semantics/openAccess