{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:40Z","timestamp":1761894700726,"version":"build-2065373602"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210172","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Efficiency and Visual-Textual Alignment for LLM-Based Radiology Report Generation"],"prefix":"10.1109","author":[{"given":"Zailong","family":"Chen","sequence":"first","affiliation":[{"name":"University of Wollongong,Dept. Computer Science,Wollongong,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University,Dept. Computer Science,Hong Kong SAR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujian","family":"Lee","sequence":"additional","affiliation":[{"name":"Beijing Normal-Hong Kong Baptist University,Zhuhai Key Laboratory of IRADS,Zhuhai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johan","family":"Barthelemy","sequence":"additional","affiliation":[{"name":"University of Wollongong,Dept. Computer Science,Wollongong,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luping","family":"Zhou","sequence":"additional","affiliation":[{"name":"The University of Sydney,Dept. Computer Science,Sydney,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Wollongong,Dept. Computer Science,Wollongong,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102510"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1240"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00943"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_52"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100033"},{"article-title":"Medxchat: Bridging cxr modalities with a unified multimodal large model","year":"2023","author":"Yang","key":"ref10"},{"article-title":"LLM-CXR: Instruction-finetuned LLM for CXR image understanding and generation","volume-title":"ICLR","author":"Lee","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102633"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-45673-2_41"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.528"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-main.47"},{"key":"ref17","article-title":"Auto-encoding knowledge graph for unsupervised medical report generation","author":"Liu","year":"2021","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"article-title":"Retrieval augmented chest x-ray report generation using openai gpt models","volume-title":"Machine Learning for Healthcare Conference","author":"Ranjit","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28038"},{"year":"2022","key":"ref21","article-title":"Introducing chatgpt"},{"year":"2023","key":"ref22","article-title":"Gpt-4 technical report"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li","key":"ref25"},{"article-title":"Investigating the catastrophic forgetting in multimodal large language models","year":"2023","author":"Zhai","key":"ref26"},{"article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","key":"ref27"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den Oord","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100802"},{"article-title":"Fixing weight decay regularization in adam","year":"2018","author":"Loshchilov","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478331"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"ICML","author":"Xu","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_63"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210172.pdf?arnumber=11210172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:46Z","timestamp":1761888826000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210172","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}