{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T05:00:22Z","timestamp":1777179622935,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Project for New Generation of AI","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976002"],"award-info":[{"award-number":["61976002"]}],"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":["62076004"],"award-info":[{"award-number":["62076004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Anhui Higher Education Institutions of China","award":["KJ2019A0033"],"award-info":[{"award-number":["KJ2019A0033"]}]},{"DOI":"10.13039\/501100011222","name":"National Laboratory of Pattern Recognition","doi-asserted-by":"publisher","award":["201900046"],"award-info":[{"award-number":["201900046"]}],"id":[{"id":"10.13039\/501100011222","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cooperative Research Project Program of Nanjing Artificial Intelligence Chip Research"},{"DOI":"10.13039\/501100011178","name":"Institute of Automation, Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011178","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3050089","type":"journal-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T18:54:12Z","timestamp":1610564052000},"page":"338-351","source":"Crossref","is-referenced-by-count":53,"title":["Adversarial-Metric Learning for Audio-Visual Cross-Modal Matching"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9820-4743","authenticated-orcid":false,"given":"Aihua","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2187-2011","authenticated-orcid":false,"given":"Menglan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-1596","authenticated-orcid":false,"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5948-5055","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2003.09.005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-015-1045-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref5","article-title":"Disjoint mapping network for cross-modal matching of voices and faces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wen","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018385"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01174"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2900171"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2928180"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/9781108891530.013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00535"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2717505"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.266"},{"key":"ref17","first-page":"1153","article-title":"Fine-grained categorization and dataset bootstrapping using deep metric learning with humans in the loop","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Yin","year":"2016"},{"key":"ref18","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2646180"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0541-x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2997184"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/94"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref30","first-page":"813","article-title":"Audio vision: Using audio-visual synchrony to locate sounds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hershey","year":"2000"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240526"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00790"},{"key":"ref37","first-page":"772","article-title":"Learning joint statistical models for audio-visual fusion and segregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fisher","year":"2001"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601119"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682383"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12329"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-139"},{"issue":"9","key":"ref46","first-page":"1751","article-title":"Generating intelligible audio speech from visual speech","volume":"25","author":"T","year":"2017","journal-title":"IEEE\/ACM Trans. Audio"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref48","article-title":"Speech-driven facial reenactment using conditional generative adversarial networks","author":"Jalalifar","year":"2018"},{"key":"ref49","first-page":"2510","article-title":"Image generation associated with music data","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Qiu","year":"2018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682970"},{"key":"ref51","article-title":"Putting a face to the voice: Fusing audio and visual signals across a video to determine speakers","author":"Hoover","year":"2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_18"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10719"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11249"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/491"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301176"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00312"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2922128"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877127"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877122"},{"key":"ref62","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky","year":"2017"},{"issue":"2605","key":"ref63","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Laurens","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref64","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","author":"Glorot","year":"2010"},{"key":"ref65","article-title":"Adam: A. method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09320535.pdf?arnumber=9320535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:04:03Z","timestamp":1704841443000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9320535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3050089","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}