{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T01:25:58Z","timestamp":1792805158069,"version":"4.5.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","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":"NSFC","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":"NSFC","doi-asserted-by":"publisher","award":["61831015"],"award-info":[{"award-number":["61831015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFE0206700"],"award-info":[{"award-number":["2021YFE0206700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"name":"Shanghai Pujiang Program","award":["22PJ1407400"],"award-info":[{"award-number":["22PJ1407400"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3251695","type":"journal-article","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T14:02:04Z","timestamp":1678975324000},"page":"1882-1896","source":"Crossref","is-referenced-by-count":128,"title":["Attention-Guided Neural Networks for Full-Reference and No-Reference Audio-Visual Quality Assessment"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5087-6559","authenticated-orcid":false,"given":"Yuqin","family":"Cao","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Key Laboratory of Digital Media Processing and Transmissions, 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 Network Engineering, Shanghai Key Laboratory of Digital Media Processing and Transmissions, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8162-1949","authenticated-orcid":false,"given":"Wei","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Key Laboratory of Digital Media Processing and Transmissions, 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 Network Engineering, Shanghai Key Laboratory of Digital Media Processing and Transmissions, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506408"},{"key":"ref2","volume-title":"Global\u20132022 Forecast Highlights"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1878022.1878030"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00018-006-6107-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2257632"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2757-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2750918"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2735192"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7350816"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB55706.2022.9828590"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2718185"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2799331"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2788206"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2018.2816783"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2017.2786023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455999"},{"issue":"1","key":"ref19","first-page":"3","article-title":"PEAQ\u2014The ITU standard for objective measurement of perceived audio quality","volume":"48","author":"Thiede","year":"2000","journal-title":"J. Audio Eng. Soc."},{"issue":"6","key":"ref20","first-page":"366","article-title":"Perceptual objective listening quality assessment (POLQA), the third generation ITU-T standard for end-to-end speech quality measurement Part I\u2014Temporal alignment","volume":"61","author":"Beerends","year":"2013","journal-title":"J. Audio Eng. Soc."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.4921674"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.23.6.061108"},{"key":"ref25","first-page":"2125","article-title":"A no-reference audio-visual video quality metric","volume-title":"Proc. 22nd Eur. Signal Process. Conf. (EUSIPCO)","author":"Martinez"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902975"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511101"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2996463"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113794"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946613"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988148"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5656-7"},{"issue":"3","key":"ref34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","article-title":"LIBSVM: A library for support vector machines","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883177"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2131660"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2002.1038064"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICMT.2011.6002087"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.837233"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2018EDP7383"},{"key":"ref41","first-page":"1","article-title":"Multimodal deep learning","volume-title":"Proc. IEEE Int. Conf. Mach. Learn.","author":"Ngiam"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937600"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45113-7_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2401732"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3023615"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548006"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3470970"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2372392"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506420"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350990"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2413944"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947352"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025098"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1117\/12.2036162"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2016.7805579"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2955024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref60","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume":"29","author":"Aytar","year":"2016","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2293423"},{"issue":"9","key":"ref62","first-page":"1","article-title":"Different audio feature extraction using segmentation","volume":"2","author":"Bhandari","year":"2016","journal-title":"Int. J. Innov. Res. Sci. Technol."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2966082"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-050753-8.50042-5"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref66","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref67","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2839890"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2966081"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10075375.pdf?arnumber=10075375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T11:35:22Z","timestamp":1707824122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10075375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3251695","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}