{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:56:42Z","timestamp":1773932202538,"version":"3.50.1"},"reference-count":59,"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":"Innovation Capability Support Program of Shaanxi","award":["2020KJXX-091"],"award-info":[{"award-number":["2020KJXX-091"]}]},{"name":"Innovation Capability Support Program of Shaanxi","award":["2020TD-015"],"award-info":[{"award-number":["2020TD-015"]}]},{"name":"National Key R&D Program of China","award":["2020YFB2103902"],"award-info":[{"award-number":["2020YFB2103902"]}]},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["61825603"],"award-info":[{"award-number":["61825603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["61925112"],"award-info":[{"award-number":["61925112"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Program of National Natural Science Foundation of China","award":["61632018"],"award-info":[{"award-number":["61632018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3071243","type":"journal-article","created":{"date-parts":[[2021,4,12]],"date-time":"2021-04-12T20:54:34Z","timestamp":1618260874000},"page":"1763-1774","source":"Crossref","is-referenced-by-count":44,"title":["Disentangled Representation Learning for Cross-Modal Biometric Matching"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8375-1181","authenticated-orcid":false,"given":"Hailong","family":"Ning","sequence":"first","affiliation":[{"name":"Key Laboratory of Spectral Imaging Technology CAS, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8398-6324","authenticated-orcid":false,"given":"Xiangtao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Spectral Imaging Technology CAS, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7037-5188","authenticated-orcid":false,"given":"Xiaoqiang","family":"Lu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Spectral Imaging Technology CAS, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an, China"}]},{"given":"Yuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cortex.2010.03.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/a0030945"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2651380"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545260"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_18"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240601"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref15","article-title":"Disentangling by partitioning: A representation learning framework for multimodal sensory data","author":"Hsu","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2962317"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2978669"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1716090115"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2019.00448"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/icd.249"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/1474704916630317"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2993960"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2965434"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.037"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2893115"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00947"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2793863"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2951636"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963957"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3020383"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.053"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682383"},{"key":"ref37","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Aytar","year":"2016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2646180"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.602"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01121"},{"key":"ref45","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref46","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Higgins","year":"2017"},{"key":"ref47","first-page":"2649","article-title":"Disentangling by factorising","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01047"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093527"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2938685"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019195"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489038"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268967"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.513"},{"key":"ref58","first-page":"119","article-title":"Oi-VAE: Output interpretable vaes for nonlinear group factor analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ainsworth","year":"2018"},{"key":"ref59","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Locatello","year":"2019"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09400909.pdf?arnumber=9400909","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:28:41Z","timestamp":1704842921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9400909\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3071243","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}