{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T20:06:12Z","timestamp":1780603572621,"version":"3.54.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176054"],"award-info":[{"award-number":["62176054"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tmi.2026.3667706","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:57:54Z","timestamp":1771966674000},"page":"3021-3038","source":"Crossref","is-referenced-by-count":0,"title":["Cogformer: A Unified Multi-Scale Brain Representation for Visual Decoding and Reconstruction From fMRI"],"prefix":"10.1109","volume":"45","author":[{"given":"Xu","family":"Yin","sequence":"first","affiliation":[{"name":"Key Laboratory of Child Development and Learning Science of Ministry of Education, School of Biological Science & Medical Engineering, Southeast University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1230-7643","authenticated-orcid":false,"given":"John Q.","family":"Gan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Electronic Engineering, University of Essex, Colchester, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8220-9737","authenticated-orcid":false,"given":"Haixian","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Child Development and Learning Science of Ministry of Education, School of Biological Science & Medical Engineering, Southeast University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102573"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2882456"},{"key":"ref3","first-page":"1","article-title":"CLIP-MUSED: CLIP-guided multi-subject visual neural information semantic decoding","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3266"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2015.08.016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3537287"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_14"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00804"},{"key":"ref9","article-title":"MoRE-brain: Routed mixture of experts for interpretable and generalizable cross-subject fMRI visual decoding","author":"Wei","year":"2025","journal-title":"arXiv:2505.15946"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613832"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(83)90190-X"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105078"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlm.2020.107325"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2024.10.004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-024-00846-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01389"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref18","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms15037"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065724500163"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263181"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","first-page":"1","article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1145"},{"key":"ref25","first-page":"1","article-title":"Large brain model for learning generic representations with tremendous EEG data in BCI","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Jiang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-021-00962-x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2995909"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106586"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"ref31","first-page":"4222","article-title":"Multi-resolution time-series transformer for long-term forecasting","volume-title":"Proc. 27th Int. Conf. Artif. Intell. Statist.","author":"Zhang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3747"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2314-15.2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1905544116"},{"key":"ref35","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref36","first-page":"24705","article-title":"Reconstructing the mind\u2019s eye: fMRI-to-image with contrastive learning and diffusion priors","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Scotti"},{"key":"ref37","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref38","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv:2205.14100"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref40","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv:2308.06721"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref42","first-page":"228","article-title":"Meteor: An automatic metric for MT evaluation with high levels of correlation with human judgments","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics (ACL)","author":"Banerjee"},{"key":"ref43","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref47","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Tan"},{"key":"ref48","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Caron"},{"key":"ref49","first-page":"1","article-title":"ITransformer: Inverted transformers are effective for time series forecasting","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Liu"},{"key":"ref50","first-page":"1","article-title":"A time series is worth 64 words: Long-term forecasting with transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nie"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"ref52","article-title":"UniBrain: Unify image reconstruction and captioning all in one diffusion model from human brain activity","author":"Mai","year":"2023","journal-title":"arXiv:2308.07428"},{"key":"ref53","first-page":"87","article-title":"Multimodal decoding of human brain activity into images and text","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Ferrante"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2148"},{"key":"ref55","first-page":"107","article-title":"Decoding natural image stimuli from fMRI data with a surface-based convolutional network","volume-title":"Proc. Int. Conf. Med. Imag. Deep Learn. (MIDL)","author":"Gu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-42891-8"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01077"},{"key":"ref58","first-page":"44038","article-title":"MindEye2: Shared-subject models enable fMRI-to-image with 1 hour of data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Scotti"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i13.33560"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00753-y"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2853-12.2013"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2016.02.066"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1097\/00004647-200110000-00001"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/S0960-9822(03)00135-0"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1403112111"},{"key":"ref66","first-page":"12214","article-title":"MindAligner: Explicit brain functional alignment for cross-subject brain visual decoding with limited data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889040"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11550367\/11408416.pdf?arnumber=11408416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:56:07Z","timestamp":1780602967000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":67,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2026.3667706","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}