136201 20260217205546.0 doi 10.1016/j.cag.2024.103983 sideral 139083 ART-2024-139083 eng Martín, Daniel Universidad de Zaragoza (orcid)0000-0002-0073-6398 tSPM-Net: A probabilistic spatio-temporal approach for scanpath prediction 2024 Access copy available to the general public Unrestricted Predicting 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. info:eu-repo/grantAgreement/ES/AEI/PID2022-141539NB-I00 info:eu-repo/grantAgreement/ES/DGA/T34-20R info:eu-repo/grantAgreement/EC/H2020/956585/EU/Predictive Rendering In Manufacture and Engineering/PRIME This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 956585-PRIME info:eu-repo/semantics/openAccess by-nc https://creativecommons.org/licenses/by-nc/4.0/deed.es 2.8 2024 COMPUTER SCIENCE, SOFTWARE ENGINEERING 53 / 129 = 0.411 2024 Q2 T2 0.569 2024 Computer Graphics and Computer-Aided Design 2024 Q2 Computer Vision and Pattern Recognition 2024 Q2 Software 2024 Q2 Engineering (miscellaneous) 2024 Q2 Signal Processing 2024 Q2 Human-Computer Interaction 2024 Q3 6.1 2024 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Gutiérrez, Diego Universidad de Zaragoza (orcid)0000-0002-7503-7022 Masia, Belén Universidad de Zaragoza (orcid)0000-0003-0060-7278 5007 570 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Lenguajes y Sistemas Inf. 122 (2024), 103983 [9 pp.] Comput. graph. COMPUTERS & GRAPHICS-UK 0097-8493 3181353 http://zaguan.unizar.es/record/136201/files/texto_completo.pdf Versión publicada 2919727 http://zaguan.unizar.es/record/136201/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:136201 articulos driver 2026-02-17-20:38:09 ARTICLE