{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T03:15:26Z","timestamp":1790651726034,"version":"4.1.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,19]]},"DOI":"10.1109\/icip42928.2021.9506408","type":"proceedings-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T17:08:41Z","timestamp":1629738521000},"page":"1429-1433","source":"Crossref","is-referenced-by-count":16,"title":["Deep Neural Networks For Full-Reference And No-Reference Audio-Visual Quality Assessment"],"prefix":"10.1109","author":[{"given":"Yuqin","family":"Cao","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Sun","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2293423"},{"key":"ref14","first-page":"1","article-title":"Different audio feature extraction using segmentation","volume":"2","author":"bhandari","year":"2016","journal-title":"International Journal of Innovative Research in Science"},{"key":"ref15","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Proc of International Conference on Neural Information Processing"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref17","article-title":"Cross-domain Deep Feature Combination for Bird Species Classification with Audio-visual Data","author":"naranchimeg","year":"2018","journal-title":"arXiv e-prints arXiv 1811 10199"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2966082"},{"key":"ref19","first-page":"1","article-title":"A multimodal saliency model for videos with high audiovisual correspondence","volume":"pp","author":"min","year":"2020","journal-title":"IEEE Transactions on Image Processing"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2750918"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2757-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.23.6.061108"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988148"},{"key":"ref8","first-page":"2125","article-title":"A no-reference audio-visual video quality metric","author":"martinez","year":"2014","journal-title":"Proceedings of the European Signal Processing Conference"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902975"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1878022.1878030"},{"key":"ref1","year":"2019","journal-title":"Avoiding the stall an operator’s guide to video qoe"},{"key":"ref9","article-title":"Deep learning based full-reference and no-reference quality assessment models for compressed ugc videos","author":"sun","year":"2021","journal-title":"arXiv preprint arXiv 2106 01111"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2015.7457921"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"2021 IEEE International Conference on Image Processing (ICIP)","location":"Anchorage, AK, USA","start":{"date-parts":[[2021,9,19]]},"end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9506008\/9506009\/09506408.pdf?arnumber=9506408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T18:57:47Z","timestamp":1670353067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9506408\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icip42928.2021.9506408","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}