{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:10:24Z","timestamp":1760119824715,"version":"build-2065373602"},"reference-count":86,"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","62225112","62271312","62132006","U24A20220"],"award-info":[{"award-number":["62401365","62225112","62271312","62132006","U24A20220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20250411","2025M773473"],"award-info":[{"award-number":["BX20250411","2025M773473"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3613957","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:40:07Z","timestamp":1759772407000},"page":"6506-6523","source":"Crossref","is-referenced-by-count":0,"title":["Subjective and Objective Audio-Visual Quality Assessment for Omnidirectional Videos"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6035-1353","authenticated-orcid":false,"given":"Xilei","family":"Zhu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-4067","authenticated-orcid":false,"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5087-6559","authenticated-orcid":false,"given":"Yuqin","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3069-060X","authenticated-orcid":false,"given":"Yucheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0542-578X","authenticated-orcid":false,"given":"Yuxin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4690-1886","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2143-7063","authenticated-orcid":false,"given":"Patrick","family":"Le Callet","sequence":"additional","affiliation":[{"name":"Polytech Nantes, Université de Nantes, Nantes, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"issue":"2","key":"ref2","first-page":"1","article-title":"Toward a practical perceptual video quality metric","volume":"6","author":"Li","year":"2016","journal-title":"Netflix Tech Blog"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00305"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988148"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3251695"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290528"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3567842"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2898732"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2955024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3028509"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240581"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123134"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-9119-8_46"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW56448.2022.9859426"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2053549"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2720693"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1117\/12.2235885"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2015.12"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICAwST.2019.8923442"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01042"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3015186"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/OJCAS.2021.3073891"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15739-6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS58744.2024.10558283"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2018.8551522"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP53017.2021.9733677"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448123"},{"issue":"1","key":"ref34","first-page":"3","article-title":"PEAQ-the ITU standard for objective measurement of perceived audio quality","volume":"48","author":"Thiede","year":"2000","journal-title":"J. Audio Eng. Soc."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1121\/1.4921674"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/app10093188"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/app9132618"},{"volume-title":"HTC Vive Pro Eye","year":"2023","key":"ref38"},{"volume-title":"Snellen Chart","year":"2020","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3549174"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-350"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2109730"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2293423"},{"key":"ref47","first-page":"121","article-title":"RASTA-PLP speech analysis","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process.","volume":"1","author":"Hermansky"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502106"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2045550"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247789"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3319332"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref63","first-page":"1","article-title":"SoundNet: Learning sound representations from unlabeled video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Aytar"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3390\/jsan10040072"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.213"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/1095878.1095882"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2548247"},{"key":"ref70","first-page":"1","article-title":"ESVQA: Perceptual quality assessment of egocentric spatial videos","volume-title":"Proc. IEEE Int. Conf. Multimedia Expo","author":"Zhu"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2651374"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref76","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref81","first-page":"73","article-title":"Bidirectional long short-term memory networks for relation classification","volume-title":"Proc. 29th Pacific Asia Conf. Lang., Inf. Comput.","author":"Zhang"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886277"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305133"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2760518"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11185324.pdf?arnumber=11185324","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T17:39:06Z","timestamp":1760117946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11185324\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3613957","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2025]]}}}