{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T14:31:31Z","timestamp":1787236291676,"version":"build-2736575974"},"reference-count":35,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061042"],"award-info":[{"award-number":["62061042"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Innovative Research Team of SEAC","award":["2018[98]"],"award-info":[{"award-number":["2018[98]"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["31920240070"],"award-info":[{"award-number":["31920240070"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education"},{"name":"Special Fund for Talent Introduction of Northwestern Nationalities University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3526954","type":"journal-article","created":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T15:25:08Z","timestamp":1736349908000},"page":"13440-13453","source":"Crossref","is-referenced-by-count":2,"title":["Combining Region-Guided Attention and Attribute Prediction for Thangka Image Captioning Method"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9593-9930","authenticated-orcid":false,"given":"Fujun","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wendong","family":"Kang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3120-5231","authenticated-orcid":false,"given":"Wenjin","family":"Hu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Linguistic and Cultural Computing of Ministry of Education, Chinese National Information Technology Research Institute, Northwest Minzu University, Lanzhou, Gansu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref5","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"Mao","year":"2014","journal-title":"arXiv:1412.6632"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref7","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref8","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"8","key":"ref18","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3064268"},{"key":"ref20","volume-title":"Research on Thangka image object detection technology based on deep learning","author":"Yuhong","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.31.4.043039"},{"key":"ref22","volume-title":"Research on Thangka image captioning generation method based on deep learning","author":"Yue","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging9080162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref25","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. Meeting Assoc. Comput. Linguistics","author":"Banerjee"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073465"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1220835.1220875"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8909458"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00483"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3042192"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10833628.pdf?arnumber=10833628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T13:59:46Z","timestamp":1737986386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10833628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3526954","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}