{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:47:34Z","timestamp":1781621254341,"version":"3.54.5"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&amp;D Program of China","award":["2022ZD0161901"],"award-info":[{"award-number":["2022ZD0161901"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276018"],"award-info":[{"award-number":["62276018"]}],"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":["U20B2069"],"award-info":[{"award-number":["U20B2069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20230484297"],"award-info":[{"award-number":["20230484297"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3358696","type":"journal-article","created":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T18:30:56Z","timestamp":1706207456000},"page":"6968-6980","source":"Crossref","is-referenced-by-count":5,"title":["MHRN: A Multimodal Hierarchical Reasoning Network for Topic Detection"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8858-7980","authenticated-orcid":false,"given":"Jiankai","family":"Li","sequence":"first","affiliation":[{"name":"State Key Laboratory of Software Development Environment and IRIP Lab, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8001-2703","authenticated-orcid":false,"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment and IRIP Lab, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5093-5635","authenticated-orcid":false,"given":"Weixin","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment and IRIP Lab, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v10i1.14778"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_63544"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3241470"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896515"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3136858"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.138"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2019.2897641"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3480246"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3119686"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462982"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964321"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-013-1391-2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428404"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01469"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1239"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.349"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0303_3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(92)90007-O"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v12i1.14983"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2838334"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622535"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2865828"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2977478"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2992485"},{"key":"ref25","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143859"},{"key":"ref27","first-page":"121","article-title":"Supervised topic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Blei","year":"2007"},{"key":"ref28","first-page":"213","article-title":"Sarcasm detection on Czech and English twitter","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Ptek","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964294"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2616279"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.230"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108153"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3164787"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120194"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096087"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3139467"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475709"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475259"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_33"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3154149"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169061"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_14"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref47","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Nagrani","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref51","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref52","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00368"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00279"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref58","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Hamilton","year":"2017"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11945"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3088307"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref67","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref68","first-page":"1","article-title":"Fixing weight decay regularization in adam","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref69","first-page":"1","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10414137.pdf?arnumber=10414137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:50:53Z","timestamp":1714762253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10414137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3358696","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}