{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T12:18:14Z","timestamp":1782735494859,"version":"3.54.5"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/bibm62325.2024.10821851","type":"proceedings-article","created":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T20:12:45Z","timestamp":1736539965000},"page":"3082-3087","source":"Crossref","is-referenced-by-count":7,"title":["Alifuse: Aligning and Fusing Multimodal Medical Data for Computer-Aided Diagnosis"],"prefix":"10.1109","author":[{"given":"Qiuhui","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Hong","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4314"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1097\/WAD.0b013e318142774e"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13764"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_6"},{"key":"ref7","article-title":"Med3d: Transfer learning for 3d medical image analysis","author":"Chen","year":"2019"},{"key":"ref8","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/S1041610209009405"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International conference on machine learning","author":"Jaegle"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02006"},{"key":"ref15","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume":"35","author":"Liang","year":"2022","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.12.044"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2007.19.9.1498"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3181cb3e25"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref20","article-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref22","article-title":"A simple baseline for zero-shot semantic segmentation with pre-trained vision-language model","author":"Xu","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20204"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-023-01045-x"}],"event":{"name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","location":"Lisbon, Portugal","start":{"date-parts":[[2024,12,3]]},"end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10821710\/10821711\/10821851.pdf?arnumber=10821851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T19:40:34Z","timestamp":1736797234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10821851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/bibm62325.2024.10821851","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}