{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T13:07:26Z","timestamp":1783602446404,"version":"3.55.0"},"reference-count":39,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3565682","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T17:32:33Z","timestamp":1745947953000},"page":"75894-75910","source":"Crossref","is-referenced-by-count":1,"title":["Research on Digital Media Art for Image Caption Generation Based on Integrated Transformer Models in CLIP"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2243-2822","authenticated-orcid":false,"given":"Lu","family":"Gao","sequence":"first","affiliation":[{"name":"School of Art Design and Creativity, Chengdu Textile College, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8850-4352","authenticated-orcid":false,"given":"Xiaofei","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Bingtuan Xingxin Vocational and Technical College, Tiemenguan City, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2010.2050411"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2598339"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.345"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.472"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2587640"},{"key":"ref11","article-title":"B-SCST: Bayesian self-critical sequence training for image captioning","author":"Bujimalla","year":"2020","journal-title":"arXiv:2004.02435"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2599174"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.494"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3638558"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298935"},{"key":"ref16","first-page":"11135","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Herdade"},{"key":"ref17","article-title":"Geometry-entangled visual semantic transformer for image captioning","author":"Cheng","year":"2021","journal-title":"arXiv:2109.14137"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00473"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00636"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.503"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01059"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2019.115776"},{"key":"ref24","article-title":"Improving image captioning with better use of captions","author":"Shi","year":"2020","journal-title":"arXiv:2006.11807"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/icce56470.2023.10043496"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3243725"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.34028\/iajit\/21\/3\/9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/e26030224"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/sym15010190"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/PCEMS58491.2023.10136098"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/w14-3348"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.wnut-1.39"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126766"},{"key":"ref39","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10979925.pdf?arnumber=10979925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T04:32:02Z","timestamp":1746592322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10979925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3565682","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}