{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:59:04Z","timestamp":1783439944799,"version":"3.54.6"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T00:00:00Z","timestamp":1744588800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T00:00:00Z","timestamp":1744588800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003471","name":"Harbin Engineering University","doi-asserted-by":"publisher","award":["KYWZ120240601"],"award-info":[{"award-number":["KYWZ120240601"]}],"id":[{"id":"10.13039\/501100003471","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,14]]},"DOI":"10.1109\/isbi60581.2025.10981029","type":"proceedings-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T17:38:51Z","timestamp":1747071531000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Parameter-Efficient Fine-Tuning Medical Multimodal Large Language Models for Medical Visual Grounding"],"prefix":"10.1109","author":[{"given":"Jinlong","family":"He","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenjun","family":"Zhong","sequence":"additional","affiliation":[{"name":"Monash University,Monash Biomedical Imaging,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_36"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230743"},{"key":"ref3","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Machine Learning for Healthcare Conference","author":"Zhang","year":"2022"},{"key":"ref4","first-page":"21372","article-title":"Medklip: Medical knowledge en-hanced language-image pre-training for x-ray diagnosis","author":"Wu","year":"2023","journal-title":"ICCV"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/isbi56570.2024.10635268"},{"key":"ref8","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref9","author":"He","year":"2024","journal-title":"Pefomed: Parameter efficient fine-tuning on multimodal large language models for medical visual question answering"},{"key":"ref10","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref11","author":"Zhu","year":"2023","journal-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models"},{"key":"ref12","author":"Chen","year":"2023","journal-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning"},{"key":"ref13","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref15","first-page":"180","article-title":"Radiology ob-jects in context (roco): a multimodal image dataset","volume-title":"CVII-STENT 2018 and Third International Workshop, LABELS 2018","author":"Pelka","year":"2018"},{"key":"ref16","first-page":"1294","article-title":"Overview of imageclefmedi-cal 2022-caption prediction and concept detection","volume-title":"CEUR Workshop Proceedings. CEUR Workshop Pro-ceedings","volume":"3180","author":"Ruckert","year":"2022"},{"key":"ref17","author":"Johnson","year":"1901","journal-title":"Mimic-cxr-jpg"},{"key":"ref18","article-title":"A comprehen-sive study of gpt-4v\u2019s multimodal capabilities in med-ical imaging","volume":"abs\/2310.20381","author":"Li","year":"2023","journal-title":"CoRR"}],"event":{"name":"2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)","location":"Houston, TX, USA","start":{"date-parts":[[2025,4,14]]},"end":{"date-parts":[[2025,4,17]]}},"container-title":["2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10980665\/10980666\/10981029.pdf?arnumber=10981029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T06:30:56Z","timestamp":1747117856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10981029\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,14]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/isbi60581.2025.10981029","relation":{},"subject":[],"published":{"date-parts":[[2025,4,14]]}}}