{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:31Z","timestamp":1777889671191,"version":"3.51.4"},"reference-count":47,"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":["N_HKUST654\/24"],"award-info":[{"award-number":["N_HKUST654\/24"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01707","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18367-18376","source":"Crossref","is-referenced-by-count":0,"title":["Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction"],"prefix":"10.1109","author":[{"given":"Haonan","family":"Wang","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qixiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lehan","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuanqi","family":"Huang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaomeng","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Wills aligner: A robust multi-subject brain representation learner","author":"Bao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1079"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-8847-5_10"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.04.127"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature18933"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i13.33560"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681229"},{"key":"ref10","first-page":"51655","article-title":"Neuroclips: Towards highfidelity and smooth fmri-to-video reconstruction","volume":"37","author":"Gong","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref12","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.05.039"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms15037"},{"key":"ref16","article-title":"Neuroanatomy, visual cortex","volume-title":"StatPearls [Internet]","author":"Huff","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref18","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"A penny for your (visual) thoughts: Self-supervised reconstruction of natural movies from brain activity","author":"Kupershmidt","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_21"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-48924-8"},{"key":"ref22","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Animate your thoughts: Decoupled reconstruction of dynamic natural vision from slow brain activity","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s00221-017-4917-4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2011.08.031"},{"issue":"8","key":"ref27","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"2","key":"ref29","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","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":"ref34","article-title":"Mindeye2: Shared-subject models enable fmri-to-image with 1 hour of data","author":"Scotti","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref36","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01389"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref39","first-page":"30","article-title":"Neural discrete representation learning","author":"Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref40","volume-title":"Diffusers: State-of-the-art diffusion models","author":"von Platen","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhab498"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhab498"},{"key":"ref43","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50821-z"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhx268"},{"key":"ref46","article-title":"Cvpr 2023 text guided video editing competition","author":"Zhangjie Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02173"}],"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\/11443530.pdf?arnumber=11443530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:07Z","timestamp":1777612447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443530\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01707","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}