{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:27:38Z","timestamp":1774420058614,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890310","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["GCS-M3VLT: Guided Context Self-Attention based Multi-modal Medical Vision Language Transformer for Retinal Image Captioning"],"prefix":"10.1109","author":[{"given":"Teja Krishna","family":"Cherukuri","sequence":"first","affiliation":[{"name":"Georgia State University,Department of Computer Science,Atlanta,GA,USA"}]},{"given":"Nagur Shareef","family":"Shaik","sequence":"additional","affiliation":[{"name":"Georgia State University,Department of Computer Science,Atlanta,GA,USA"}]},{"given":"Jyostna Devi","family":"Bodapati","sequence":"additional","affiliation":[{"name":"Technology & Reserach University,Vignan’s Foundation for Science,Guntur,Andhra Pradesh,India"}]},{"given":"Dong Hye","family":"Ye","sequence":"additional","affiliation":[{"name":"Georgia State University,Department of Computer Science,Atlanta,GA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2337\/diacare.26.9.2653"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-03043-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2014.84"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.122.4.615"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00249"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446878"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506803"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00331"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463667"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00190"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.104946"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icip51287.2024.10647584"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25100"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72378-0_67"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"ref19","article-title":"Visiongpt: Vision-language understanding agent using generalized multimodal framework","author":"Kelly","year":"2024"},{"key":"ref20","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"10096","article-title":"Efficientnetv2: Smaller models and faster training","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icip51287.2024.10647604"},{"key":"ref23","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"8","key":"ref24","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref25","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890310.pdf?arnumber=10890310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:10Z","timestamp":1774416370000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890310","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}