000162446 001__ 162446
000162446 005__ 20251017144635.0
000162446 0247_ $$2doi$$a10.1016/j.cag.2022.06.002
000162446 0248_ $$2sideral$$a129122
000162446 037__ $$aART-2022-129122
000162446 041__ $$aeng
000162446 100__ $$0(orcid)0000-0002-5275-8652$$aBernal Berdun, Edurne$$uUniversidad de Zaragoza
000162446 245__ $$aSST-Sal: A spherical spatio-temporal approach for saliency prediction in 360 videos
000162446 260__ $$c2022
000162446 5060_ $$aAccess copy available to the general public$$fUnrestricted
000162446 5203_ $$aVirtual reality (VR) has the potential to change the way people consume content, and has been predicted to become the next big computing paradigm. However, much remains unknown about the grammar and visual language of this new medium, and understanding and predicting how humans behave in virtual environments remains an open problem. In this work, we propose a novel saliency prediction model which exploits the joint potential of spherical convolutions and recurrent neural networks to extract and model the inherent spatio-temporal features from 360° videos. We employ Convolutional Long Short-Term Memory cells (ConvLSTMs) to account for temporal information at the time of feature extraction rather than to post-process spatial features as in previous works. To facilitate spatio-temporal learning, we provide the network with an estimation of the optical flow between 360° frames, since motion is known to be a highly salient feature in dynamic content. Our model is trained with a novel spherical Kullback–Leibler Divergence (KLDiv) loss function specifically tailored for saliency prediction in 360° content. Our approach outperforms previous state-of-the-art works, being able to mimic human visual attention when exploring dynamic 360° videos.
000162446 536__ $$9info:eu-repo/grantAgreement/ES/AEI/PID2019-105004GB-I00$$9info:eu-repo/grantAgreement/EC/H2020/682080/EU/Intuitive editing of visual appearance from real-world datasets/CHAMELEON$$9This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 682080-CHAMELEON$$9info:eu-repo/grantAgreement/EC/H2020/956585/EU/Predictive Rendering In Manufacture and Engineering/PRIME$$9This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 956585-PRIME
000162446 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttps://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
000162446 590__ $$a2.5$$b2022
000162446 591__ $$aCOMPUTER SCIENCE, SOFTWARE ENGINEERING$$b52 / 108 = 0.481$$c2022$$dQ2$$eT2
000162446 592__ $$a0.539$$b2022
000162446 593__ $$aComputer Graphics and Computer-Aided Design$$c2022$$dQ2
000162446 593__ $$aComputer Vision and Pattern Recognition$$c2022$$dQ2
000162446 593__ $$aEngineering (miscellaneous)$$c2022$$dQ2
000162446 593__ $$aSignal Processing$$c2022$$dQ2
000162446 593__ $$aHuman-Computer Interaction$$c2022$$dQ3
000162446 593__ $$aSoftware$$c2022$$dQ3
000162446 594__ $$a4.9$$b2022
000162446 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000162446 700__ $$0(orcid)0000-0002-0073-6398$$aMartín Serrano, Daniel$$uUniversidad de Zaragoza
000162446 700__ $$0(orcid)0000-0002-7503-7022$$aGutiérrez Pérez, Diego$$uUniversidad de Zaragoza
000162446 700__ $$0(orcid)0000-0003-0060-7278$$aMasiá Corcoy, Belén$$uUniversidad de Zaragoza
000162446 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf.
000162446 773__ $$g106 (2022), 200-209$$pComput. graph.$$tCOMPUTERS & GRAPHICS-UK$$x0097-8493
000162446 8564_ $$s17972271$$uhttps://zaguan.unizar.es/record/162446/files/texto_completo.pdf$$yPostprint
000162446 8564_ $$s2887919$$uhttps://zaguan.unizar.es/record/162446/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000162446 909CO $$ooai:zaguan.unizar.es:162446$$particulos$$pdriver
000162446 951__ $$a2025-10-17-14:28:27
000162446 980__ $$aARTICLE