{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T10:35:11Z","timestamp":1781951711211,"version":"3.54.5"},"reference-count":48,"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":["62432006"],"award-info":[{"award-number":["62432006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276159"],"award-info":[{"award-number":["62276159"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004480","name":"Fundamental Research Program of Shanxi Province","doi-asserted-by":"publisher","award":["202303021223004"],"award-info":[{"award-number":["202303021223004"]}],"id":[{"id":"10.13039\/501100004480","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3628469","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:50:58Z","timestamp":1762800658000},"page":"7321-7334","source":"Crossref","is-referenced-by-count":1,"title":["Local Alignment for Medical Vision-Language Pre-Training"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8342-7605","authenticated-orcid":false,"given":"Huimin","family":"Yan","sequence":"first","affiliation":[{"name":"Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1496-8923","authenticated-orcid":false,"given":"Xian","family":"Yang","sequence":"additional","affiliation":[{"name":"Alliance Manchester Business School, The University of Manchester, Manchester, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0380-2995","authenticated-orcid":false,"given":"Liang","family":"Bai","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5887-9327","authenticated-orcid":false,"given":"Jiye","family":"Liang","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3171081"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3534436"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02504-3"},{"key":"ref4","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3558446"},{"key":"ref6","first-page":"56186","article-title":"Med-UniC: Unifying cross-lingual medical vision-language pre-training by diminishing bias","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"ref8","article-title":"Large-scale domain-specific pretraining for biomedical vision-language processing","author":"Zhang","year":"2023","journal-title":"arXiv:2303.00915"},{"key":"ref9","first-page":"25081","article-title":"EmbodiedGPT: Vision-language pre-training via embodied chain of thought","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02532"},{"key":"ref11","first-page":"17283","article-title":"Grounding language models to images for multimodal inputs and outputs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref13","first-page":"1236","article-title":"Local contrastive learning for medical image recognition","volume-title":"Proc. AMIA Annu. Symp.","author":"Rizvi"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3325965"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref16","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":"ref17","first-page":"415","article-title":"Leveraging coarse-to-fine grained representations in contrastive learning for differential medical visual question answering","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent.","author":"Xiao"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"ref19","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2025.3528196"},{"key":"ref21","first-page":"1","article-title":"LLaVA-Med: Training a large language-and-vision assistant for biomedicine in one day","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref22","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3582689"},{"key":"ref25","first-page":"35959","article-title":"PyramidCLIP: Hierarchical feature alignment for vision-language model pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gao"},{"key":"ref26","first-page":"1","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yao"},{"key":"ref27","first-page":"32942","article-title":"Coarse-to-fine vision-language pre-training with fusion in the backbone","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dou"},{"key":"ref28","first-page":"1","article-title":"Interpretable sparse system identification: Beyond recent deep learning techniques on time-series prediction","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3204444"},{"key":"ref30","article-title":"Contrastive localized language-image pre-training","author":"Chen","year":"2024","journal-title":"arXiv:2410.02746"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3416052"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01059"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00425-9"},{"key":"ref36","article-title":"Multi-modal vision-language model for generalizable annotation-free pathology localization and clinical diagnosis","author":"Yang","year":"2024","journal-title":"arXiv:2401.02044"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103299"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_39"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","article-title":"Publicly available clinical BERT embeddings","author":"Alsentzer","year":"2019","journal-title":"arXiv:1904.03323"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104319"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_44"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01092"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-73507-8_7"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11237022.pdf?arnumber=11237022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:43:35Z","timestamp":1763405015000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11237022\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3628469","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}