{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:19:45Z","timestamp":1792786785984,"version":"4.5.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/tdmrep.html"}],"funder":[{"name":"Beijing Nova Program","award":["20230484368"],"award-info":[{"award-number":["20230484368"]}],"id":[{"id":"https:\/\/ror.org\/033pgsq69","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3683701","type":"journal-article","created":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T19:36:23Z","timestamp":1776195383000},"page":"10391-10404","source":"Crossref","is-referenced-by-count":1,"title":["BIMM: Brain-Inspired Masked Modeling for Video Representation Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8899-3996","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2742-3613","authenticated-orcid":false,"given":"Zhifan","family":"Wan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Nie","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changzhen","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8348-392X","authenticated-orcid":false,"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3024-4404","authenticated-orcid":false,"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref4","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref5","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref6","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref7","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021","journal-title":"arXiv:2103.11886"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref10","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Xie"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref15","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref18","article-title":"DeepMIM: Deep supervision for masked image modeling","author":"Ren","year":"2023","journal-title":"arXiv:2303.08817"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref20","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(92)90344-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.163.3870.895"},{"key":"ref23","volume-title":"Principles of Neural Science","volume":"4","author":"Kandel","year":"2000"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CSICC58665.2023.10105321"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abq7592"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/S0952523800005423"},{"issue":"1","key":"ref27","first-page":"371","article-title":"Adaptive V1-MT model for motion perception","volume":"13","author":"Li","year":"2019","journal-title":"KSII Trans. Internet Inf. Syst."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref30","article-title":"Self-supervised video representation learning with motion-aware masked autoencoders","author":"Yang","year":"2022","journal-title":"arXiv:2210.04154"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1049\/ji-3-2.1946.0074"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref33","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169469"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3141051"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01003"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_25"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_17"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3290938"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(97)00011-7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-023-01876-9"},{"key":"ref57","first-page":"36","article-title":"A dual-stream neural network explains the functional segregation of dorsal and ventral visual pathways in human brains","volume-title":"Proc. NeurIPS","author":"Minkyu"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2994740"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref60","article-title":"Training deeper convolutional networks with deep supervision","author":"Wang","year":"2015","journal-title":"arXiv:1505.02496"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544037.ch14"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00211"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref67","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00815"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_5"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00517"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00222"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01241"},{"key":"ref77","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":"ref78","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Han"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00153"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_26"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref85","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00267"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01787"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01768"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11481118.pdf?arnumber=11481118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T22:12:02Z","timestamp":1792707122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11481118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":89,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3683701","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}