{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T23:17:13Z","timestamp":1784330233564,"version":"3.55.0"},"reference-count":77,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036005"],"award-info":[{"award-number":["62036005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2021.3128254","type":"journal-article","created":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T20:30:12Z","timestamp":1637094612000},"page":"515-528","source":"Crossref","is-referenced-by-count":44,"title":["Cross-Modal Variational Auto-Encoder for Content-Based Micro-Video Background Music Recommendation"],"prefix":"10.1109","volume":"25","author":[{"given":"Jing","family":"Yi","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6266-2788","authenticated-orcid":false,"given":"Yaochen","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7882-1066","authenticated-orcid":false,"given":"Zhenzhong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"ref2","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Chen","year":"2011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413540"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3019710"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2646180"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350974"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.001"},{"key":"ref14","first-page":"604","article-title":"Query by video: Cross-modal music retrieval","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Li","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref16","article-title":"A comprehensive survey on cross-modal retrieval","author":"Wang","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351055"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350894"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060291"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2957948"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.888013"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967245"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366341"},{"key":"ref25","first-page":"2643","article-title":"Deep content-based music recommendation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Oord","year":"2013"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3389\/fams.2019.00044"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2018.04.004"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3405962.3405963"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/511"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2846092"},{"key":"ref31","article-title":"Tunesensor: A semantic-driven music recommendation service for digital photo albums","volume-title":"Proc. Int. Semantic Web Conf.","author":"Chao","year":"2011"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195068276.001.0001"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654919"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14442-9_33"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1017\/S0954579405050340"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/BIGCOMP.2017.7881714"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASONAM49781.2020.9381371"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-04117-9_26"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396325"},{"key":"ref40","first-page":"711","article-title":"Cross-modal embeddings for video and audio retrieval","volume-title":"Proc. Eur. Conf. Comput. Vis. Workshops","author":"Surs","year":"2018"},{"key":"ref41","article-title":"Youtube-8 m: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2557722"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206046"},{"key":"ref44","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref45","first-page":"37","article-title":"Autoencoders, unsupervised learning and deep architectures","volume-title":"Proc. Int. Conf. Unsupervised Transfer Learn. Workshop","author":"Baldi","year":"2011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2010.09.004"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186150"},{"key":"ref48","first-page":"5712","article-title":"Learning disentangled representations for recommendation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098077"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IPCCC50635.2020.9391524"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3270323.3270326"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3270323.3270329"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3111487"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18178\/wcse.2019.06.016"},{"key":"ref61","first-page":"5575","article-title":"Multimodal generative models for scalable weakly-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502097"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11991"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413676"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.498"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2897586"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.108.171"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.12"},{"key":"ref73","first-page":"15 692","article-title":"Variational mixture-of-experts autoencoders for multi-modal deep generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shi","year":"2019"},{"key":"ref74","article-title":"Joint multimodal learning with deep generative models","volume-title":"Proc. Int. Conf. Learn. Representations Workshops","author":"Suzuki","year":"2017"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467376"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462875"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467289"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09616385.pdf?arnumber=9616385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:57:07Z","timestamp":1705021027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9616385\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3128254","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}