{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T14:18:50Z","timestamp":1776435530848,"version":"3.51.2"},"reference-count":44,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation for Distinguished Young Scholars of China","award":["62125201"],"award-info":[{"award-number":["62125201"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176230"],"award-info":[{"award-number":["62176230"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2021.3122542","type":"journal-article","created":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T21:47:12Z","timestamp":1636408032000},"page":"167-178","source":"Crossref","is-referenced-by-count":58,"title":["Joint Embedding of Deep Visual and Semantic Features for Medical Image Report Generation"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5598-1692","authenticated-orcid":false,"given":"Yan","family":"Yang","sequence":"first","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6478-9192","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang International Studies University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7227-3671","authenticated-orcid":false,"given":"Weidong","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University, Hangzhou, China"}]},{"given":"Hanliang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Regional Medical Center for National Institute of Respiratory Diseases, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2015.2393193"},{"issue":"107","key":"ref2","first-page":"1","article-title":"Interleaved text\/image deep mining on a large-scale radiology database for automated image interpretation","volume":"17","author":"Shin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.356"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1240"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00943"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(88)90021-0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref13","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","volume-title":"Proc. 15th Conf. Comput. Natural Lang. Learn.","author":"Li","year":"2011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref15","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Ordonez","year":"2011"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2889922"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2904878"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941820"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2894139"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951226"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896494"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.445"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"ref27","first-page":"685","article-title":"Auto-encoding scene graphs for image captioning","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","volume":"10","author":"Yang","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.274"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_52"},{"key":"ref30","first-page":"1537","article-title":"Hybrid retrieval-generation reinforced agent for medical image report generation","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Li","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016666"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1657"},{"issue":"144","key":"ref33","first-page":"1","article-title":"Addressing data bias problems for chest X-ray image report generation","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Harzig","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32226-7_80"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-18590-9_64"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref39","first-page":"188","article-title":"NegBio: A high-performance tool for negation and uncertainty detection in radiology reports","author":"Peng","year":"2018","journal-title":"AMIA Inform. Summit"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref44","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out, Post- Conf. Workshop ACL","author":"Lin","year":"2004"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09606584.pdf?arnumber=9606584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:02:32Z","timestamp":1705024952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9606584\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3122542","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}