{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:49:33Z","timestamp":1781020173694,"version":"3.54.1"},"reference-count":48,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100018615","name":"General Project of Philosophy and Social Science Research for Higher Education Institutions in Jiangsu Province","doi-asserted-by":"publisher","award":["2024SJYB0834"],"award-info":[{"award-number":["2024SJYB0834"]}],"id":[{"id":"10.13039\/501100018615","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003448","name":"General Project of Educational Science Research at Xuzhou University of Technology","doi-asserted-by":"publisher","award":["YGJ2424"],"award-info":[{"award-number":["YGJ2424"]}],"id":[{"id":"10.13039\/501100003448","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3571624","type":"journal-article","created":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T17:58:16Z","timestamp":1747677496000},"page":"88472-88483","source":"Crossref","is-referenced-by-count":2,"title":["FGMFN: Fine-Grained Multiscale Cross-Modal Sentiment Analysis in Advertisements"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3296-8595","authenticated-orcid":false,"given":"Han","family":"Wang","sequence":"first","affiliation":[{"name":"School of Design, Xuzhou University of Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Du","sequence":"additional","affiliation":[{"name":"School of Design, Xuzhou University of Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/002224379503200201"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.149"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.04.010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2501643.2501648"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1282280.1282290"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2955637"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/a9020041"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102141"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2012.2217397"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref12","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2012.212"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1126004.1126005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3025171.3025186"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.041"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.349"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160060"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3178204"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2024.0150290"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747542"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2957872"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29540"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/95"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2916838"},{"key":"ref33","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2018.11.006"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43639-5_7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/751"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2034"},{"key":"ref40","first-page":"25","article-title":"Convolutional neural networks for sentence classification","volume":"6","author":"Rakhlin","year":"2016","journal-title":"GitHub"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301371"},{"key":"ref43","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2022.3231746"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.519"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-17685-9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10685-z"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11007133.pdf?arnumber=11007133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T04:43:42Z","timestamp":1748061822000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11007133\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3571624","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}