{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T05:43:24Z","timestamp":1781243004854,"version":"3.54.1"},"reference-count":46,"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":["62471418"],"award-info":[{"award-number":["62471418"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fujian Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2024J01058"],"award-info":[{"award-number":["2024J01058"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Science and Technology Special Project of Fujian Province","award":["2024HZ022003"],"award-info":[{"award-number":["2024HZ022003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3571672","type":"journal-article","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T18:09:49Z","timestamp":1748282989000},"page":"3169-3180","source":"Crossref","is-referenced-by-count":19,"title":["STPNet: Scale-Aware Text Prompt Network for Medical Image Segmentation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6389-7428","authenticated-orcid":false,"given":"Dandan","family":"Shan","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0622-4710","authenticated-orcid":false,"given":"Yunxiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, UT Southwestern Medical Center, Dallas, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5998-7565","authenticated-orcid":false,"given":"Qingde","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Hull, Hull, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0498-0432","authenticated-orcid":false,"given":"Jie","family":"Tian","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Automation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9996-6870","authenticated-orcid":false,"given":"Qingqi","family":"Hong","sequence":"additional","affiliation":[{"name":"Center for Digital Media Computing, School of Film, the National Institute for Data Science in Health and Medicine, and the Institute of Artificial Intelligence, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2996645"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108109"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00729"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15937-4_65"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2022.10.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2021.3056564"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3027738"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3067047"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3291719"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_15"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-024-01051-8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43901-8_69"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109512"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959609"},{"key":"ref17","article-title":"Attention U-Net: Learning where to look for the pancreas","author":"Oktay","year":"2018","journal-title":"arXiv:1804.03999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref20","article-title":"SAM2-UNet: Segment anything 2 makes strong encoder for natural and medical image segmentation","author":"Xiong","year":"2024","journal-title":"arXiv:2408.08870"},{"key":"ref21","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref22","first-page":"29582","article-title":"Class-aware adversarial transformers for medical image segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07859-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04306"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-022-02325-w"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2023.107493","article-title":"MESTrans: Multi-scale embedding spatial transformer for medical image segmentation","volume":"233","author":"Liu","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00332"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3508752"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096683"},{"key":"ref33","article-title":"Exploring transfer learning in medical image segmentation using vision-language models","author":"Poudel","year":"2023","journal-title":"arXiv:2308.07706"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref36","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"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","article-title":"Publicly available clinical BERT embeddings","author":"Alsentzer","year":"2019","journal-title":"arXiv:1904.03323"},{"key":"ref39","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","author":"Hu","year":"2023","journal-title":"arXiv:2311.17117"},{"key":"ref40","article-title":"Towards data-efficient learning: A benchmark for COVID-19 CT lung and infection segmentation","author":"Ma","year":"2020","journal-title":"arXiv:2004.12537"},{"key":"ref41","article-title":"MosMedData: Chest CT scans with COVID-19 related findings dataset","author":"Morozov","year":"2020","journal-title":"arXiv:2005.06465"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s13755-021-00146-8"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37734-2_37"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"ref45","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref46","article-title":"LAVT: Language-aware vision transformer for referring image segmentation","author":"Yang","year":"2021","journal-title":"arXiv:2112.02244"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11015682.pdf?arnumber=11015682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T05:54:00Z","timestamp":1748930040000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11015682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3571672","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}