{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:46:16Z","timestamp":1753602376646,"version":"3.37.3"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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":["62372003"],"award-info":[{"award-number":["62372003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2308085Y40","2208085J18"],"award-info":[{"award-number":["2308085Y40","2208085J18"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2022-036"],"award-info":[{"award-number":["GXXT-2022-036"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3390573","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T17:40:39Z","timestamp":1713375639000},"page":"8698-8709","source":"Crossref","is-referenced-by-count":2,"title":["Public-Private Attributes-Based Variational Adversarial Network for Audio-Visual Cross-Modal Matching"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9820-4743","authenticated-orcid":false,"given":"Aihua","family":"Zheng","sequence":"first","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation and the Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Artificial Intelligence, Anhui University, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4071-3086","authenticated-orcid":false,"given":"Fan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0288-2937","authenticated-orcid":false,"given":"Haichuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation and the Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Artificial Intelligence, Anhui University, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3059-798X","authenticated-orcid":false,"given":"Jiaxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8934-9537","authenticated-orcid":false,"given":"Chao","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Hefei University, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7233-2739","authenticated-orcid":false,"given":"Chenglong","family":"Li","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation and the Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Artificial Intelligence, Anhui University, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102605"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01803"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3163445"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3079897"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3326694"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref10","article-title":"Disjoint mapping network for cross-modal matching of voices and faces","author":"Wen","year":"2018","journal-title":"arXiv:1807.04836"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050089"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01608"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3066038"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531364"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222936"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_25"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413710"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3243725"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00075"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097207"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3199496"},{"key":"ref24","article-title":"Adversarial autoencoders","author":"Makhzani","year":"2015","journal-title":"arXiv:1511.05644"},{"key":"ref25","article-title":"The variational fair autoencoder","author":"Louizos","year":"2015","journal-title":"arXiv:1511.00830"},{"key":"ref26","article-title":"Importance weighted autoencoders","author":"Burda","year":"2015","journal-title":"arXiv:1509.00519"},{"article-title":"Variational lossy autoencoder","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chen","key":"ref27"},{"key":"ref28","first-page":"19667","article-title":"NVAE: A deep hierarchical variational autoencoder","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Vahdat"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3202370"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3189027"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178144"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253799"},{"key":"ref33","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969793"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01173"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-103"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.404"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3188462"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/94"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401302"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6845"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3615863"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00041"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10504144.pdf?arnumber=10504144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T05:53:14Z","timestamp":1727761994000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10504144\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":49,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3390573","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}