{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T06:09:38Z","timestamp":1778652578493,"version":"3.51.4"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62088102"],"award-info":[{"award-number":["62088102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX2021239"],"award-info":[{"award-number":["BX2021239"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01790","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19258-19268","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Brain Decoding: Visual-Semantic Reconstructions to Mental Creation Extension Based on fMRI"],"prefix":"10.1109","author":[{"given":"Haodong","family":"Jing","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongyao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqiang","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibo","family":"Hua","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Huang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-021-00962-x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref3","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee","year":"2005"},{"key":"ref4","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"6","volume-title":"Rethinking visual reconstruction: Experience-based content completion guided by visual cues","author":"Chen","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3572784"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02569"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/brainsci12020228"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.tbench.2024.100152"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0663"},{"key":"ref12","article-title":"Brain captioning: Decoding human brain activity into images and text","author":"Ferrante","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.01.021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2015.00023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.27.070203.144220"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms15037"},{"key":"ref19","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP55214.2022.9943383"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref22","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref23","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","first-page":"5","article-title":"Brainclip: Bridging brain and visual-linguistic representation via clip for generic natural visual stimulus decoding from fmri","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature06976"},{"key":"ref27","first-page":"2","article-title":"Unibrain: Unify image reconstruction and captioning all in one diffusion model from human brain activity","author":"Mai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00107"},{"key":"ref29","first-page":"5","volume-title":"Introducing meta llama 3: The most capable openly available 11 m to date","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.08.007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-021-00921-6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2012.06.011"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00030"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","first-page":"5","article-title":"Adversarial diffusion distillation","author":"Sauer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Reconstructing the mind\u2019s eye: fmri-to-image with contrastive learning and diffusion priors","volume":"36","author":"Scotti","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","article-title":"Mindeye2: Shared-subject models enable fmri-to-image with 1 hour of data","author":"Scotti","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3113"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2021.03.042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01389"},{"key":"ref45","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan","year":"2019"},{"key":"ref46","first-page":"2","article-title":"Aligning brain functions boosts the decoding of visual semantics in novel subjects","author":"Thual","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01077"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00804"},{"key":"ref52","article-title":"Umbrae: Unified multimodal decoding of brain signals","author":"Xia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28519"},{"key":"ref54","first-page":"5","article-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/abc902"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444855.pdf?arnumber=11444855","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T05:22:58Z","timestamp":1778649778000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444855\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01790","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}