{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:40:17Z","timestamp":1770846017943,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T00:00:00Z","timestamp":1765756800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T00:00:00Z","timestamp":1765756800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1109\/bibm66473.2025.11356102","type":"proceedings-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:19:40Z","timestamp":1769721580000},"page":"2790-2797","source":"Crossref","is-referenced-by-count":0,"title":["EVLM-Net: Vision-Language Fusion with Efficient Upsampling for Accurate Polyp Segmentation"],"prefix":"10.1109","author":[{"given":"Jiangpeng","family":"Shi","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology,Taiyuan,China,030024"}]},{"given":"Lina","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Software, Taiyuan University of Technology,Taiyuan,China,030024"}]},{"given":"Juanjuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology,Taiyuan,China,030024"}]},{"given":"Yan","family":"Qiang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology,Taiyuan,China,030024"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-025-00106-w"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01118"},{"key":"ref6","article-title":"Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Attention u-net: Learning where to look for the pancreas","author":"Oktay","year":"2018","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.00219"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref17","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier gans","volume-title":"International conference on machine learning","author":"Odena","year":"2017"},{"key":"ref18","first-page":"29441","article-title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","volume-title":"International conference on machine learning","author":"Ryali","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_24"},{"issue":"8","key":"ref20","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref21","article-title":"Exploring transfer learning in medical image segmentation using vision-language models","author":"Poudel","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_66"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_12"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109555"}],"event":{"name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","location":"Wuhan, China","start":{"date-parts":[[2025,12,15]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11355913\/11355975\/11356102.pdf?arnumber=11356102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:52:21Z","timestamp":1770843141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11356102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,15]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/bibm66473.2025.11356102","relation":{},"subject":[],"published":{"date-parts":[[2025,12,15]]}}}