{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:31:53Z","timestamp":1770845513418,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"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":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342904","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"1544-1549","source":"Crossref","is-referenced-by-count":0,"title":["Align Modalities: Advancing Medical Report Generation with Unified Encoder and Inter-Case Contrastive Learning"],"prefix":"10.1109","author":[{"given":"Haoquan","family":"Chen","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology,Beijing Laboratory of Intelligent Information Technology, School of Computer Science,Beijing,China"}]},{"given":"Mingtao","family":"Pei","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,Beijing Laboratory of Intelligent Information Technology, School of Computer Science,Beijing,China"}]},{"given":"Zhengang","family":"Nie","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref2","first-page":"16266","article-title":"Auto-encoding knowledge graph for unsupervised medical report generation","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3197162"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/1754-9485.12014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"ref6","first-page":"1537","article-title":"Hybrid retrieval-generation reinforced agent for medical image report generation","author":"Li","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.234"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20204"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102798"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM55620.2022.9995533"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref16","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref17","first-page":"19730","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref19","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531374"},{"key":"ref21","article-title":"Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment","author":"Zhu","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1657"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100033"},{"key":"ref28","article-title":"Radialog: A large vision-language model for radiology report generation and conversational assistance","author":"Pellegrini","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121260"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad1995"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"ref34","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28279"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101817"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102633"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.clinicalnlp-1.24"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3393018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5692-6_23"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref43","first-page":"85","article-title":"Meteor 1.3: Automatic metric for reliable optimization and evaluation of machine translation systems","volume-title":"Proceedings of the Workshop on Statistical Machine Translation (SMT)","author":"Denkowski"},{"key":"ref44","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref45","article-title":"Decoupled weight decay regularization","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Loshchilov"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342904.pdf?arnumber=11342904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:57Z","timestamp":1770843057000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342904\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342904","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}