{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T03:28:53Z","timestamp":1775186933628,"version":"3.50.1"},"reference-count":40,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228227","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["MicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report Generation"],"prefix":"10.1109","author":[{"given":"Amaan","family":"Izhar","sequence":"first","affiliation":[{"name":"Universiti Malaya,Faculty of Computer Science and Information Technology,Kuala Lumpur,Malaysia"}]},{"given":"Nurul","family":"Japar","sequence":"additional","affiliation":[{"name":"Universiti Malaya,Faculty of Computer Science and Information Technology,Kuala Lumpur,Malaysia"}]},{"given":"Norisma","family":"Idris","sequence":"additional","affiliation":[{"name":"Universiti Malaya,Faculty of Computer Science and Information Technology,Kuala Lumpur,Malaysia"}]},{"given":"Ting","family":"Dang","sequence":"additional","affiliation":[{"name":"The University of Melbourne,School of Computing and Information Systems,Melbourne,Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2021.100557"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10651198"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-025-10404-6"},{"key":"ref4","first-page":"249","article-title":"Clinically accurate chest x-ray report generation","volume-title":"Machine Learning for Healthcare Conference","author":"Liu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1117\/12.2653672"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101817"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref9","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-022-01013-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-022-02738-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-023-03046-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-025-01411-y"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3393018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222405"},{"key":"ref19","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017"},{"issue":"120","key":"ref20","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.221"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_58"},{"key":"ref23","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref25","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72378-0_67"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1240"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref30","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the Acl Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee"},{"key":"ref31","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.836"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1155\/2024\/6680546"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.09.084"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228227.pdf?arnumber=11228227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:26:59Z","timestamp":1763191619000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228227","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}