{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T17:45:47Z","timestamp":1780595147048,"version":"3.54.1"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["62206200"],"award-info":[{"award-number":["62206200"]}],"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":["62206137"],"award-info":[{"award-number":["62206137"]}],"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":["62376196"],"award-info":[{"award-number":["62376196"]}],"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":["62036012"],"award-info":[{"award-number":["62036012"]}],"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":["U23A20387"],"award-info":[{"award-number":["U23A20387"]}],"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":["62322212"],"award-info":[{"award-number":["62322212"]}],"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":["62072455"],"award-info":[{"award-number":["62072455"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Tianjin Natural Science Foundation","doi-asserted-by":"publisher","award":["22JCQNJC00940"],"award-info":[{"award-number":["22JCQNJC00940"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Tianjin Natural Science Foundation","doi-asserted-by":"publisher","award":["22JCYBJC00030"],"award-info":[{"award-number":["22JCYBJC00030"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004763","name":"Natural Science Foundation of Inner Mongolia Autonomous Region","doi-asserted-by":"publisher","award":["2022MS06025"],"award-info":[{"award-number":["2022MS06025"]}],"id":[{"id":"10.13039\/501100004763","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tcsvt.2024.3362270","type":"journal-article","created":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T18:49:08Z","timestamp":1707158948000},"page":"5728-5741","source":"Crossref","is-referenced-by-count":17,"title":["A Versatile Multimodal Learning Framework for Zero-Shot Emotion Recognition"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1461-7100","authenticated-orcid":false,"given":"Fan","family":"Qi","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3183-9218","authenticated-orcid":false,"given":"Huaiwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-9755","authenticated-orcid":false,"given":"Xiaoshan","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3363560"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2719043"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3163445"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3247822"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5662-9"},{"key":"ref6","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. ICML","author":"Ngiam"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17686"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.06.005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.140"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240633"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475647"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20895"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2019.01606"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.81.4.684"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461963"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916866"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532431"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/\/0022-3514.52.6.1061"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1702247114"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1037\/10366-003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1037\/a0038025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00124"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8724"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2622690"},{"key":"ref27","article-title":"Action2 Vec: A crossmodal embedding approach to action learning","author":"Hahn","year":"2019","journal-title":"arXiv:1901.00484"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10466"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0893-6"},{"key":"ref30","article-title":"TARN: Temporal attentive relation network for few-shot and zero-shot action recognition","author":"Bishay","year":"2019","journal-title":"arXiv:1907.09021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.325"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"issue":"2","key":"ref33","first-page":"1","article-title":"Multi-label image classification with a probabilistic label enhancement model","volume-title":"Proc. UAI","volume":"1","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16345"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref36","first-page":"1","article-title":"Simple spectral graph convolution","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00313"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093438"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01030"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00089"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3276075"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2016.7574736"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-010-0702-0"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01424"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612442"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2553579"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3007352"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3144804"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2808760"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014889"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3072412"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035285"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2006.873781"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3134167"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312858"},{"key":"ref57","volume-title":"A dynamic and Dual-Process Theory of Humor","author":"Li","year":"2015"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2008.03.005"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1488"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.128"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.15"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_28"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00012"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00294"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.02.002"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3173815"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3262754"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.644"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00068"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00880"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00861"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3295772"},{"key":"ref74","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2109","journal-title":"arXiv:2109.08472"},{"key":"ref75","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284977"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1352"},{"key":"ref79","article-title":"End-to-end video classification with knowledge graphs","author":"Yuan","year":"2017","journal-title":"arXiv:1711.01714"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240566"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3188547"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667014"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.03.001"},{"key":"ref84","first-page":"1","article-title":"Learning with local and global consistency","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"16","author":"Zhou"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-012-0314-x"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165180"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2396531"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2432791"},{"key":"ref90","first-page":"9","article-title":"IJCNLP-2017 task 2: Dimensional sentiment analysis for Chinese phrases","volume-title":"Proc. IJCNLP","author":"Yu"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01312"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00880"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00068"},{"key":"ref94","article-title":"Open vocabulary multi-label classification with dual-modal decoder on aligned visual-textual features","author":"Xu","year":"2022","journal-title":"arXiv:2208.09562"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2015.7178964"},{"key":"ref97","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"arXiv:2010.11929"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10582818\/10419371.pdf?arnumber=10419371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,4]],"date-time":"2024-07-04T04:04:10Z","timestamp":1720065850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10419371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":98,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3362270","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}