{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T04:19:40Z","timestamp":1747887580141,"version":"3.41.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2037","U22B2051","62176222","62176223","62176226","62072386","62072387","62072389","62002305","62272401"],"award-info":[{"award-number":["U21B2037","U22B2051","62176222","62176223","62176226","62072386","62072387","62072389","62002305","62272401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2019B1515120049"],"award-info":[{"award-number":["2019B1515120049"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of Fujian Province of China","doi-asserted-by":"publisher","award":["2021J01002","2022J06001"],"award-info":[{"award-number":["2021J01002","2022J06001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chengdu Philosophy and Social Science Planning Project","award":["2022CZ154"],"award-info":[{"award-number":["2022CZ154"]}]},{"name":"Sichuan Philosophy and Social Science Planning Project","award":["SC22SZ006"],"award-info":[{"award-number":["SC22SZ006"]}]},{"DOI":"10.13039\/501100012226","name":"China Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["20720220068"],"award-info":[{"award-number":["20720220068"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3243952","type":"journal-article","created":{"date-parts":[[2023,2,10]],"date-time":"2023-02-10T19:36:12Z","timestamp":1676057772000},"page":"14500-14510","source":"Crossref","is-referenced-by-count":1,"title":["Semantic-Guided Selective Representation for Image Captioning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9620-8241","authenticated-orcid":false,"given":"Yinan","family":"Li","sequence":"first","affiliation":[{"name":"Media Analytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8744-3423","authenticated-orcid":false,"given":"Yiwei","family":"Ma","sequence":"additional","affiliation":[{"name":"Media Analytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5110-4526","authenticated-orcid":false,"given":"Yiyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Media Analytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-9295","authenticated-orcid":false,"given":"Xiao","family":"Yu","sequence":"additional","affiliation":[{"name":"Digital Governance Laboratory, Sichuan Administration Institute, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref11","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","volume-title":"Proc. 13th Conf. Eur. Chapter Assoc. Comput. Linguistics","author":"Mitchell"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.306"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref14","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Ordonez"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413877"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350943"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123275"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413901"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011317"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2904878"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref25","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/app8050739"},{"key":"ref30","first-page":"11137","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Herdade"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref37","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020","journal-title":"arXiv:2004.00849"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00325"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref41","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00898"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3185320"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.014"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3155795"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01751"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3093725"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref56","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref59","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10041895.pdf?arnumber=10041895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:40:50Z","timestamp":1747849250000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10041895\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3243952","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}