{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T08:17:57Z","timestamp":1777623477488,"version":"3.51.4"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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":["62173324"],"award-info":[{"award-number":["62173324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006223"],"award-info":[{"award-number":["62006223"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"International Partnership Program of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["104GJHZ2022013GC"],"award-info":[{"award-number":["104GJHZ2022013GC"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tnnls.2023.3264730","type":"journal-article","created":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T18:39:55Z","timestamp":1682966395000},"page":"12772-12783","source":"Crossref","is-referenced-by-count":30,"title":["BViT: Broad Attention-Based Vision Transformer"],"prefix":"10.1109","volume":"35","author":[{"given":"Nannan","family":"Li","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9356-0610","authenticated-orcid":false,"given":"Yaran","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weifan","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5902-9073","authenticated-orcid":false,"given":"Zixiang","family":"Ding","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8078-6829","authenticated-orcid":false,"given":"Shuai","family":"Nie","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref3","article-title":"Pay attention to MLPs","author":"Liu","year":"2021","journal-title":"arXiv:2105.08050"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2998497"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2890334"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2956965"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2022.3230858"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-021-00308-x"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref16","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Raghu"},{"key":"ref17","article-title":"Do wide and deep networks learn the same things? Uncovering how neural network representations vary with width and depth","author":"Nguyen","year":"2020","journal-title":"arXiv:2010.15327"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3067028"},{"key":"ref20","article-title":"MLP-Mixer: An all-MLP architecture for vision","author":"Tolstikhin","year":"2021","journal-title":"arXiv:2105.01601"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref23","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01206"},{"key":"ref28","article-title":"UniNet: Unified architecture search with convolution, transformer, and MLP","author":"Liu","year":"2021","journal-title":"arXiv:2110.04035"},{"key":"ref29","first-page":"1","article-title":"Recurrent models of visual attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Mnih"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2020.1003228"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2614675"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.446"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/431"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/307"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1174"},{"key":"ref41","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3143201"},{"key":"ref43","article-title":"Stacked BNAS: Rethinking broad convolutional neural network for neural architecture search","author":"Ding","year":"2021","journal-title":"arXiv:2111.07722"},{"key":"ref44","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pham"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3078573"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2919608"},{"key":"ref48","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref49","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00815"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref58","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref61","article-title":"ResMLP: Feedforward networks for image classification with data-efficient training","author":"Touvron","year":"2021","journal-title":"arXiv:2105.03404"},{"key":"ref62","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Han"},{"key":"ref63","first-page":"1","article-title":"A kernel statistical test of independence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"20","author":"Gretton"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10663876\/10113704.pdf?arnumber=10113704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T01:49:54Z","timestamp":1733881794000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10113704\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":64,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3264730","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}