{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:26:28Z","timestamp":1770845188731,"version":"3.50.1"},"reference-count":31,"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\/smc58881.2025.11343186","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"1799-1804","source":"Crossref","is-referenced-by-count":0,"title":["ACFormer: A Multimodal Attention and Contrastive Learning Framework for Chest Disease Risk Prediction"],"prefix":"10.1109","author":[{"given":"Tao","family":"Lin","sequence":"first","affiliation":[{"name":"Shanghai Institute of Technology,Shanghai,China"}]},{"given":"Yiheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Institute of Technology,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Machine Learning (ICML)","author":"Kim"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Machine Learning (ICML)","author":"Radford"},{"key":"ref4","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Machine Learning (ICML)","author":"Jia"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref6","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Machine Learning (ICML)","author":"Li"},{"issue":"1","key":"ref7","first-page":"271","article-title":"Pulmonary nodule auxiliary diagnosis method based on deep transfer learning","volume":"46","author":"Zhang","year":"2020","journal-title":"Computer Engineering"},{"issue":"4","key":"ref8","first-page":"727","article-title":"Classification of breast cancer pathological images based on Cycle-GAN and improved DPN network","volume":"56","author":"Zhang","year":"2022","journal-title":"J. Zhejiang Univ. (Engineering Science)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2999816"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/embc44109.2020.9175288"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3224727"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"issue":"3","key":"ref13","first-page":"238","article-title":"Medical image fusion with local-global feature coupling and cross-scale attention","volume":"49","author":"Zhang","year":"2023","journal-title":"Computer Engineering"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2022.3192431"},{"issue":"8","key":"ref15","first-page":"2456","article-title":"Spatial Attention-Guided Multimodal Fusion Network with Deformable Convolution for Brain Tumor Segmentation","volume":"68","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref16","first-page":"104289","article-title":"Cross-modal Contrastive Learning for NSCLC Survival Analysis with CT Images and Electronic Health Records","volume":"138","author":"Xu","year":"2023","journal-title":"J. Biomed. Inform."},{"issue":"1","key":"ref17","first-page":"1548","article-title":"Multimodal Survival Prediction in Ovarian Cancer Using Deep Learning on Whole Slide Images, Clinical Data, and Radiomics","volume":"13","author":"Boehm","year":"2022","journal-title":"Nat. Commun."},{"key":"ref18","first-page":"102856","article-title":"Entity-Centric Medical Vision-Language Pre-training for Chest X-ray Report Generation","volume":"88","author":"Zhou","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref19","article-title":"CLIP: Learning Transferable Visual Models from Natural Language Supervision","author":"Radford","year":"2019"},{"key":"ref20","article-title":"MIMIC-CXR-JPG - chest radiographs with structured labels (version 2.0.0)","volume-title":"PhysioNet","author":"Johnson","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1161\/01.CTR.101.23.e215"},{"key":"ref23","article-title":"Medaugment: Universal automatic data augmentation plug-in for medical image analysis","author":"Liu","year":"2023"},{"key":"ref24","article-title":"Augmix: A simple data processing method to improve robustness and uncertainty","author":"Hendrycks","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971225"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3195212"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","article-title":"Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.378"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2955476"}],"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\/11343186.pdf?arnumber=11343186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:09Z","timestamp":1770843009000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11343186","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}