{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:01:17Z","timestamp":1783573277605,"version":"3.55.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62201341"],"award-info":[{"award-number":["62201341"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02092","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22529-22538","source":"Crossref","is-referenced-by-count":2,"title":["Learnable Retrieval Enhanced Visual-Text Alignment and Fusion for Radiology Report Generation"],"prefix":"10.1109","author":[{"given":"Qin","family":"Zhou","sequence":"first","affiliation":[{"name":"ECUST,Department of Computer Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoyan","family":"Liang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xindi","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"ECUST,Department of Computer Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Yao","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sai","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01346"},{"key":"ref3","article-title":"Fine-grained image-text alignment in medical imaging enables cyclic image-report generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref5","article-title":"Cross-modal memory networks for radiology report generation","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref8","first-page":"85","article-title":"Meteor 1.3: Automatic metric for reliable optimization and evaluation of machine translation systems","volume-title":"Proceedings of the sixth workshop on statistical machine translation","author":"Denkowski","year":"2011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01745"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28038"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3308295"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00268"},{"key":"ref17","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102633"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.241"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1511.08458"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"ref29","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_11"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3426359"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01954"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20204"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102510"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102798"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_13"},{"key":"ref40","article-title":"Otseg: Multi-prompt sinkhorn attention for zero-shot semantic segmentation","volume-title":"The 18th European Conference on Computer Vision, ECCV 2024. European Computer Vision Association (ECVA)","author":"Chul Ye","year":"2024"},{"key":"ref41","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_63"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446878"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444042.pdf?arnumber=11444042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:29:13Z","timestamp":1777530553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444042\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02092","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}