{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:02:12Z","timestamp":1781881332228,"version":"3.54.5"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01979","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21310-21320","source":"Crossref","is-referenced-by-count":2,"title":["GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-Ray Diagnosis"],"prefix":"10.1109","author":[{"given":"Bo","family":"Liu","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University,Hong Kong S.A.R.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Zou","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li-Ming","family":"Zhan","sequence":"additional","affiliation":[{"name":"Ningbo University of Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zexin","family":"Lu","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Hong Kong S.A.R.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Dong","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Hong Kong S.A.R.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yidi","family":"Chen","sequence":"additional","affiliation":[{"name":"West China Hospital of Sichuan University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengqiang","family":"Xie","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Hong Kong S.A.R.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiannong","family":"Cao","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Hong Kong S.A.R.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Ming","family":"Wu","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Hong Kong S.A.R.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huazhu","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing, Agency for Science, Technology and Research,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Minigpt-med: Large language model as a general interface for radiology diagnosis","author":"Alkhaldi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0170"},{"issue":"2","key":"ref5","first-page":"3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","author":"Bai","year":"2023","journal-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond"},{"key":"ref7","article-title":"Overview of the vqa-med task at imageclef 2021: Visual question answering and generation in the medical domain","volume-title":"Proceedings of the CLEF 2021 Conference and Labs of the Evaluation Forum-working notes","author":"Ben Abacha"},{"key":"ref8","article-title":"Detecting and evaluating medical hallucinations in large vision language models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Eyegpt: Ophthalmic assistant with large language models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02139"},{"issue":"3","key":"ref12","first-page":"6","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 % chatgpt quality"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463584"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"ref16","article-title":"Pathvqa: $30000+$ questions for medical visual question answering","author":"He","year":"2020","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599819"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02093"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref20","article-title":"Mistral 7b","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref25","article-title":"Llm-cxr: Instruction-finetuned llm for cxr image understanding and generation","author":"Lee","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_34"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3232411"},{"key":"ref32","article-title":"Competence-based multimodal curriculum learning for med-ical report generation","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017"},{"key":"ref35","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3207502"},{"key":"ref37","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":"ref38","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh","year":"2021"},{"key":"ref39","article-title":"Medgemma technical report","author":"Sellergren","year":"2025","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Xraygpt: Chest radiographs summarization using medical visionlanguage models","author":"Thawkar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07894-z"},{"key":"ref43","article-title":"Towards generalist foundation model for radiology","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae045"},{"key":"ref45","article-title":"Chest imagenome dataset for clinical reasoning","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Multi-modal pre-training for medical vision-language understanding and generation: An empirical study with a new benchmark","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3507000"},{"key":"ref48","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","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":"ref50","article-title":"Bertscore: Evaluating text generation with bert","author":"Zhang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Pmc-vqa: Visual instruction tuning for medical visual question answering","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Radgenome-chest ct: A grounded vision-language dataset for chest ct analysis","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.74"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3398350"},{"key":"ref55","article-title":"Skingpt-4: an interactive dermatology diagnostic system with visual large language model","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Medrg: Medical report grounding with multi-modal large language model","author":"Zou","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444163.pdf?arnumber=11444163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:41:31Z","timestamp":1777531291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444163\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01979","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}