{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:10:35Z","timestamp":1784301035710,"version":"3.55.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401365"],"award-info":[{"award-number":["62401365"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225112"],"award-info":[{"award-number":["62225112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271312"],"award-info":[{"award-number":["62271312"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132006"],"award-info":[{"award-number":["62132006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20220"],"award-info":[{"award-number":["U24A20220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Oceanic Interdisciplinary Program of Shanghai Jiao Tong University","award":["SL2020ZD102"],"award-info":[{"award-number":["SL2020ZD102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3567842","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:49:03Z","timestamp":1747158543000},"page":"3447-3462","source":"Crossref","is-referenced-by-count":9,"title":["How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Model"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0542-578X","authenticated-orcid":false,"given":"Yuxin","family":"Zhu","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-4067","authenticated-orcid":false,"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1620-736X","authenticated-orcid":false,"given":"Kaiwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3069-060X","authenticated-orcid":false,"given":"Yucheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"USC-SJTU Institute of Cultural and Creative Industry, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6035-1353","authenticated-orcid":false,"given":"Xilei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5568-0849","authenticated-orcid":false,"given":"Long","family":"Teng","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4133-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2018.8351786"},{"key":"ref3","article-title":"Perceptual quality assessment of omnidirectional audio-visual signals","author":"Zhu","year":"2023","journal-title":"arXiv:2307.10813"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2793599"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2966864"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_25"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10182000"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3337066"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3172971"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366154"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451338"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3304109.3325818"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383267"},{"key":"ref18","first-page":"241","article-title":"Predicting human gaze using low-level saliency combined with face detection","volume-title":"Proc. NIPS","author":"Cerf"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1167\/8.7.32"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587715"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995676"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995506"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.147"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3461956"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-010-9074-z"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1167\/14.8.5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-3435-5_16"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2015.7457921"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2015.08.004"},{"key":"ref31","article-title":"DAVE: A deep audio-visual embedding for dynamic saliency prediction","author":"Tavakoli","year":"2019","journal-title":"arXiv:1905.10693"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00482"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/OJID.2024.3351089"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858783"},{"key":"ref35","first-page":"488","article-title":"Saliency detection in 360\u00b0 videos","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Zhang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897737"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3306596"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW46912.2020.9105956"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP49819.2020.9301766"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-46317-4_29"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2018.8551543"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00154"},{"key":"ref44","first-page":"305","article-title":"ATSal: An attention based architecture for saliency prediction in 360\u00b0 videos","volume-title":"Proc. Pattern Recognit. ICPR Int. Workshops Challenges","author":"Dahou"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","volume-title":"Insta360. Insta360 Pro 2","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296592"},{"key":"ref48","volume-title":"Siti-Tools","author":"Robitza","year":"2022"},{"key":"ref49","volume-title":"Introduction to Audio Analysis: A MATLAB\u00ae Approach","author":"Giannakopoulos","year":"2014"},{"key":"ref50","volume-title":"Vive Pro Eye","author":"Business","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3220404"},{"key":"ref52","volume-title":"Unity","author":"Technologies","year":"2023"},{"key":"ref53","volume-title":"Media Player","author":"Video","year":"2023"},{"key":"ref54","volume-title":"Facebook-360-Spatial-Workstation","author":"Archive","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3304109.3325820"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.image.2018.05.003","article-title":"Toolbox and dataset for the development of saliency and scanpath models for omnidirectional\/360\u00b0 still images","volume":"69","author":"Guti\u00e9rrez","year":"2018","journal-title":"Signal Process., Image Commun."},{"key":"ref58","first-page":"360","article-title":"Self-supervised generation of spatial audio for 360\u00b0 video","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","volume":"31","author":"Morgado"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2005.03.019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.16910\/jemr.6.4.1"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2210727"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1167\/7.14.4"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900174"},{"key":"ref70","article-title":"SalGAN: Visual saliency prediction with generative adversarial networks","author":"Pan","year":"2017","journal-title":"arXiv:1701.01081"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2851672"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547955"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00248"},{"key":"ref74","first-page":"182","article-title":"Simple vs complex temporal recurrences for video saliency prediction","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Linardos"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02575"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2022.06.002"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522440"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.71"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.275"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240669"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01045"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947352"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00886"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506089"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3576857"},{"key":"ref88","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.16527"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11003418.pdf?arnumber=11003418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T04:50:51Z","timestamp":1750395051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11003418\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3567842","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}