{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T03:22:35Z","timestamp":1774927355873,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R &amp; D Program of China","award":["2020AAA0108303"],"award-info":[{"award-number":["2020AAA0108303"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["41876098"],"award-info":[{"award-number":["41876098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ARC","award":["DP200103223"],"award-info":[{"award-number":["DP200103223"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tpami.2025.3562866","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T17:40:26Z","timestamp":1745343626000},"page":"6585-6598","source":"Crossref","is-referenced-by-count":1,"title":["Diagnostic Captioning by Cooperative Task Interactions and Sample-Graph Consistency"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2079-4931","authenticated-orcid":false,"given":"Zhanyu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, University of Sydney, Camperdown, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0961-0441","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0403-1923","authenticated-orcid":false,"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8762-2424","authenticated-orcid":false,"given":"Luping","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, University of Sydney, Camperdown, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.171"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2015.2393193"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46976-8_13"},{"key":"ref4","article-title":"Exploring nearest neighbor approaches for image captioning","author":"Devlin","year":"2015","journal-title":"arXiv:1505.04467"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref11","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. Assoc. Comput. Linguistics","author":"Devlin"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1103"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1240"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00083"},{"key":"ref18","article-title":"ImageSem at ImageCLEF 2018 caption task: Image retrieval and transfer learning","volume-title":"Proc. Conf. Labs Eval. Forum","author":"Wang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00246"},{"key":"ref20","article-title":"RadGraph: Extracting clinical entities and relations from radiology reports","author":"Jain","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00483"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","first-page":"2361","article-title":"Review networks for caption generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.356"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32226-7_80"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_52"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20351-1_10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1657"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102798"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102510"},{"key":"ref38","first-page":"16266","article-title":"Auto-encoding knowledge graph for unsupervised medical report generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_10"},{"key":"ref42","first-page":"11135","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Herdade"},{"key":"ref43","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref45","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1410"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1075"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"ref54","first-page":"1537","article-title":"Hybrid retrieval-generation reinforced agent for medical image report generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016666"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1093\/jamia\/ocv080","article-title":"Preparing a collection of radiology examinations for distribution and retrieval","volume":"23","author":"Dina","year":"2016","journal-title":"J. Amer. Med. Inform. Assoc."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref60","first-page":"311","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Conf. Assoc. Comput. Linguistics","author":"Lin"},{"key":"ref61","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref63","first-page":"4566","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100033"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102633"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2947134"},{"key":"ref68","article-title":"BERTScore: Evaluating text generation with BERT","author":"Zhang","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100802"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2024.3408456"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11068886\/10974505.pdf?arnumber=10974505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T22:57:11Z","timestamp":1751929031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10974505\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":70,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3562866","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}