{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T13:25:31Z","timestamp":1784294731813,"version":"3.55.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62076227"],"award-info":[{"award-number":["62076227"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2023AFB572"],"award-info":[{"award-number":["2023AFB572"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020725","name":"Hubei Key Laboratory of Intelligent Geo-Information Processing","doi-asserted-by":"publisher","award":["KLIGIP-2022-B10"],"award-info":[{"award-number":["KLIGIP-2022-B10"]}],"id":[{"id":"10.13039\/100020725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535292","type":"journal-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T18:49:44Z","timestamp":1741114184000},"page":"3766-3780","source":"Crossref","is-referenced-by-count":12,"title":["Emotion-Oriented Cross-Modal Prompting and Alignment for Human-Centric Emotional Video Captioning"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8873-4778","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, China University of Geosciences, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0465-3976","authenticated-orcid":false,"given":"Yuanyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, China University of Geosciences, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2697-3383","authenticated-orcid":false,"given":"Shunping","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science, China University of Geosciences, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science, China University of Geosciences, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6515-7696","authenticated-orcid":false,"given":"Chang","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science, China University of Geosciences, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3055-2493","authenticated-orcid":false,"given":"Wujie","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Cisco-La Trobe Centre for AI and IoT, School of Computing, Engineering and Mathematical Sciences, La Trobe University, Bundoora, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2022.103058"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3359045"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222965"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3241517"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3058555"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611726"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"ref11","article-title":"Taking an emotional look at video paragraph captioning","author":"Li","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183402"},{"key":"ref13","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3192709"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3134190"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2897330"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681601"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548190"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102204"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3343520"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3130939"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102366"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"issue":"2","key":"ref29","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","volume":"1","author":"Kenton","year":"2019"},{"issue":"140","key":"ref30","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"issue":"8","key":"ref31","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25412"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01434"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27981"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00536"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/173"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref43","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Chen","year":"2011"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13292"},{"key":"ref46","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref47","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref49","article-title":"Microsoft Coco Captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref50","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00901"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01109"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3058626"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/481"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00427"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10909571.pdf?arnumber=10909571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T17:43:27Z","timestamp":1749750207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10909571\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535292","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}