{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:18Z","timestamp":1777888638758,"version":"3.51.4"},"reference-count":64,"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\/501100010909","name":"Young Scientists Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62304162"],"award-info":[{"award-number":["62304162"]}],"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":["2024M762532"],"award-info":[{"award-number":["2024M762532"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007128","name":"Shaanxi Provincial Natural Science Foundation for Basic Research Program","doi-asserted-by":"publisher","award":["2024JC-YBMS-794"],"award-info":[{"award-number":["2024JC-YBMS-794"]}],"id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["XJSJ24090"],"award-info":[{"award-number":["XJSJ24090"]}],"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\/iccv51701.2025.01852","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19914-19924","source":"Crossref","is-referenced-by-count":1,"title":["An Efficient Hybrid Vision Transformer for Tinyml Applications"],"prefix":"10.1109","author":[{"given":"Fanhong","family":"Zeng","sequence":"first","affiliation":[{"name":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanan","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juntao","family":"Guan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Fan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Wu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xilong","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Lai","sequence":"additional","affiliation":[{"name":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","article-title":"Mmdetection: Open mmlab detection toolbox and benchmark","author":"Chen","year":"2019","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref6","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref7","volume-title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark.","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref11","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Learned step size quantization","author":"Esser","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref14","volume-title":"fvcore library","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref17","article-title":"Learning both weights and connections for efficient neural network","volume":"28","author":"Han","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Fastervit: Fast vision transformers with hierarchical attention","author":"Hatamizadeh","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref22","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0940"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3297620"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_1"},{"key":"ref34","article-title":"Mobilevit: lightweight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Separable selfattention for mobile vision transformers","author":"Mehta","year":"2022","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"Molchanov","year":"2016","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"ref39","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref40","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref42","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref43","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref44","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01506"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref51","author":"Wightman","year":"2019","journal-title":"Pytorch image models"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref53","first-page":"30392","article-title":"Early convolutions help transformers see better","volume":"34","author":"Xiao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.15203"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_40"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20387"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00550"},{"key":"ref59","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref62","article-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"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\/11444368.pdf?arnumber=11444368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:52:16Z","timestamp":1777611136000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01852","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}