{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:13:16Z","timestamp":1778080396541,"version":"3.51.4"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017413","name":"Innovation Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017413","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1109\/bibm62325.2024.10822152","type":"proceedings-article","created":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T20:12:45Z","timestamp":1736539965000},"page":"3784-3789","source":"Crossref","is-referenced-by-count":5,"title":["EyeGraphGPT: Knowledge Graph Enhanced Multimodal Large Language Model for Ophthalmic Report Generation"],"prefix":"10.1109","author":[{"given":"Zhirui","family":"Wang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinlong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenlong","family":"Gao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Dong","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Dai","sequence":"additional","affiliation":[{"name":"Changsha Aier Eye Hospital,Institute of Digital Ophthalmology and Visual Science,Hunan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingjie","family":"Yan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wuliang","family":"Huang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Ffa-ir: Towards an explainable and reliable medical report generation benchmark","volume-title":"Thirty-fifth conference on neural information processing systems datasets and benchmarks track (round 2)","author":"Li"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00249"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506803"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463667"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00331"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00190"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02000"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_59"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385537"},{"key":"ref10","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref11","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2021.100557"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"ref16","first-page":"5989","article-title":"Jpg-jointly learn to align: Automated disease prediction and radiology report generation","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"You"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00268"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.246"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385817"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385596"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref26","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"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103357"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547948"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkh061"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1101\/2023.01.10.23284412","article-title":"Medklip: Medical knowledge enhanced language-image pre-training in radiology","author":"Wu","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"ref34","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Language is not all you need: Aligning perception with language models","volume":"36","author":"Huang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9781316584989.004"},{"key":"ref38","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref39","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref42","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5034"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012757468803412"},{"key":"ref46","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref47","article-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref49","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"}],"event":{"name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","location":"Lisbon, Portugal","start":{"date-parts":[[2024,12,3]]},"end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10821710\/10821711\/10822152.pdf?arnumber=10822152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T09:47:57Z","timestamp":1736588877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10822152\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/bibm62325.2024.10822152","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}