{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T02:01:00Z","timestamp":1772935260356,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["25ZR1401266"],"award-info":[{"award-number":["25ZR1401266"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11401943","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"6241-6247","source":"Crossref","is-referenced-by-count":0,"title":["MEVLERG: Medical Vision-Language Encoder for Report Generation"],"prefix":"10.1109","author":[{"given":"Songwen","family":"Pei","sequence":"first","affiliation":[{"name":"University of Shanghai For Science and Technology,China,200093"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfeng","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Shanghai For Science and Technology,China,200093"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Cong","sequence":"additional","affiliation":[{"name":"University of Shanghai For Science and Technology,China,200093"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Donghua University,China,201620"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"19730","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00742-2"},{"key":"ref4","article-title":"Clinicallongformer and clinical-bigbird: Transformers for long clinical sequences","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Emerging Properties in Unified Multimodal Pretraining","author":"Deng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01112"},{"key":"ref7","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3617233.3617246"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16876-5_3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-31223-5"},{"key":"ref11","article-title":"Medmoe: Mixture of domain-specific experts for lightweight medical visionlanguage models","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43895-0_10"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_4"},{"key":"ref14","article-title":"Medslip: Medical dual-stream language-image pretraining for fine-grained alignment","author":"Fan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Large-scale and fine-grained vision-language pre-training for enhanced ct image understanding","author":"Shui","year":"2025","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref17","article-title":"Convllava: Hierarchical backbones as visual encoder for large multimodal models","author":"Ge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref19","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref22","article-title":"Huatuogpt-vision, towards injecting medical visual knowledge into multimodal 11 ms at scale","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref24","article-title":"Healthgpt: A medical large vision-language model for unifying comprehension and generation via heterogeneous knowledge adaptation","author":"Lin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Lcm-lora: A universal stable-diffusion acceleration module","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1984"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28717"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5114\/wo.2014.47136"},{"key":"ref31","article-title":"Pathvqa: 30000+ questions for medical visual question answering","author":"He","year":"2020","journal-title":"arXiv preprint"},{"key":"ref32","first-page":"353","article-title":"Med-flamingo: a multimodal medical few-shot learner","volume-title":"Machine Learning for Health (ML4H)","author":"Moor","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"ref34","first-page":"19730","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"ref36","volume-title":"CXR-PRO: MIMICCXR with Prior References Omitted","author":"Vignav","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300138"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11401943.pdf?arnumber=11401943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:27:53Z","timestamp":1772868473000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11401943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11401943","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}