{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T22:45:27Z","timestamp":1758149127473,"version":"3.44.0"},"reference-count":33,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576049","62177034"],"award-info":[{"award-number":["62576049","62177034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Peking University People’s Hospital Scientific Research Development Funds","award":["RDJ 2022-33"],"award-info":[{"award-number":["RDJ 2022-33"]}]},{"name":"BUPT Excellent Ph.D. Students Foundation","award":["CX2021120"],"award-info":[{"award-number":["CX2021120"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3602392","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:51:04Z","timestamp":1756155064000},"page":"3510-3514","source":"Crossref","is-referenced-by-count":0,"title":["Eliminating Non-Overlapping Semantic Misalignment for Cross-Modal Medical Retrieval"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1901-3819","authenticated-orcid":false,"given":"Zeqiang","family":"Wei","sequence":"first","affiliation":[{"name":"School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-2990","authenticated-orcid":false,"given":"Zeyi","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1458-4118","authenticated-orcid":false,"given":"Xiuzhuang","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref8","first-page":"1","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref9","first-page":"1","article-title":"RadGraph: Extracting clinical entities and relations from radiology reports","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Jain","year":"2021"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3178899"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_39"},{"article-title":"Deep supervised information bottleneck hashing for cross-modal retrieval based computer-aided diagnosis","year":"2022","author":"Shi","key":"ref16"},{"key":"ref17","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01935"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"article-title":"Masked contrastive reconstruction for cross-modal medical image-report retrieval","year":"2023","author":"Wei","key":"ref22"},{"key":"ref23","first-page":"385","article-title":"Pragmatic radiology report generation","volume-title":"Proc. 3rd Mach. Learn. Health Symp.","author":"Nguyen","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.514"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91721-9_2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"ref27","first-page":"56382","article-title":"Unlocking the power of spatial and temporal information in medical multimodal pre-training","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Yang","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32890"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3325965"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01093"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1056\/AIdbp2401120"},{"key":"ref32","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao","year":"2022"},{"article-title":"CheXpert plus: Augmenting a large chest X-ray dataset with text radiology reports, patient demographics and additional image formats","year":"2024","author":"Chambon","key":"ref33"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/11141016.pdf?arnumber=11141016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:37:01Z","timestamp":1758044221000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11141016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3602392","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2025]]}}}