{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:23Z","timestamp":1777865303275,"version":"3.51.4"},"reference-count":54,"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\/501100004731","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LR24F020002"],"award-info":[{"award-number":["LR24F020002"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China (NSFC)","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\/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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02037","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21938-21948","source":"Crossref","is-referenced-by-count":0,"title":["Bridging the Gap Between Brain and Machine in Interpreting Visual Semantics: Towards Self-Adaptive Brain-to-Text Decoding"],"prefix":"10.1109","author":[{"given":"Jiaxuan","family":"Chen","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Qi","sequence":"additional","affiliation":[{"name":"Zhejiang University,MOE Frontier Science Center for Brain Science and Brain-Machine Integration"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueming","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"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","article-title":"From voxels to pixels and back: Self-supervision in natural-image reconstruction from fmri","author":"Beliy","year":"2019","journal-title":"Advances in Neural Information Processing Systems, 32"},{"key":"ref4","article-title":"Large scale gan training for high fidelity natural image synthesis","author":"Brock","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref5","first-page":"4856","article-title":"Rethinking visual reconstruction: Experience-based content completion guided by visual cues","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Chen","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02569"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3572784"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.18.1.193"},{"key":"ref12","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0663"},{"key":"ref14","article-title":"Brain captioning: Decoding human brain activity into images and text","author":"Ferrante","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2022.119121"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms15037"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1126\/science.1234330"},{"key":"ref20","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature06713"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref23","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073465"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613832"},{"key":"ref27","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 arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2008.11.004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206960"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892673"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroscience.2020.07.040"},{"issue":"8","key":"ref33","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref34","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":"ref35","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.795488"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.07.043"},{"key":"ref39","first-page":"36","article-title":"Reconstructing the mind\u2019s eye: fmri-to-image with contrastive learning and diffusion priors","author":"Scotti","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2019.00021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006633"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3113"},{"key":"ref43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0541"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01389"},{"key":"ref46","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 preprint arXiv"},{"key":"ref47","first-page":"30","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems, 30"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00753-y"},{"key":"ref51","article-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlpdemos.6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00804"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_14"}],"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\/11444138.pdf?arnumber=11444138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:11:05Z","timestamp":1777529465000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444138\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02037","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}