{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T06:33:36Z","timestamp":1779086016389,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018550","name":"Science and Technology Innovation (STI) 2030 Major Projects","doi-asserted-by":"publisher","award":["2021ZD0200403"],"award-info":[{"award-number":["2021ZD0200403"]}],"id":[{"id":"10.13039\/501100018550","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024BSSXM11"],"award-info":[{"award-number":["2024BSSXM11"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["624B2127"],"award-info":[{"award-number":["624B2127"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017940","name":"Zhejiang Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["LR24F020002"],"award-info":[{"award-number":["LR24F020002"]}],"id":[{"id":"10.13039\/100017940","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3572784","type":"journal-article","created":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T18:04:21Z","timestamp":1748887461000},"page":"3281-3293","source":"Crossref","is-referenced-by-count":7,"title":["MindGPT: Interpreting What You See With Non-Invasive Brain Recordings"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4387-9671","authenticated-orcid":false,"given":"Jiaxuan","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory of Brain-Machine Intelligence, College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9789-8907","authenticated-orcid":false,"given":"Yu","family":"Qi","sequence":"additional","affiliation":[{"name":"Affiliated Mental Health Center and Hangzhou Seventh People’s Hospital, the MOE Frontier Science Center for Brain Science and Brain-Machine Integration, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7742-0722","authenticated-orcid":false,"given":"Yueming","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Brain-Machine Intelligence, College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4049-6181","authenticated-orcid":false,"given":"Gang","family":"Pan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Brain-Machine Intelligence, College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-021-00921-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-023-01304-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0051-13.2013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2011.10.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref6","first-page":"4856","article-title":"Rethinking visual reconstruction: Experience-based content completion guided by visual cues","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Chen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01389"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"ref9","first-page":"1","article-title":"Reconstructing the mind\u2019s eye: Fmri-to-image with contrastive learning and diffusion priors","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Scotti"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00804"},{"key":"ref11","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":"ref12","article-title":"Brain captioning: Decoding human brain activity into images and text","author":"Ferrante","year":"2023","journal-title":"arXiv:2305.11560"},{"key":"ref13","article-title":"Improving visual image reconstruction from human brain activity using latent diffusion models via multiple decoded inputs","author":"Takagi","year":"2023","journal-title":"arXiv:2306.11536"},{"issue":"8","key":"ref14","first-page":"1","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00107"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191262"},{"key":"ref18","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv:2205.14100"},{"key":"ref19","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat6766"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4244"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1126\/science.1063736"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nn1444"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263181"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2009.11.064"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.22087"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2016.00351"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1931"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nature06713"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms15037"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2009.09.006"},{"key":"ref37","first-page":"1","article-title":"From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Beliy"},{"key":"ref38","first-page":"29624","article-title":"Mind reader: Reconstructing complex images from brain activities","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref39","article-title":"Cinematic mindscapes: High-quality video reconstruction from brain activity","author":"Chen","year":"2023","journal-title":"arXiv:2305.11675"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006633"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2019.00021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2020.117602"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3028167"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206960"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892673"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613832"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.ne.18.030195.001205"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-021-00962-x"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073465"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref62","first-page":"1","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref64","first-page":"13038","article-title":"Reconstructing perceptive images from brain activity by shape-semantic GAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fang"},{"issue":"86","key":"ref65","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00209"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-021-02975-5"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11018227.pdf?arnumber=11018227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T17:47:46Z","timestamp":1749664066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11018227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3572784","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}