{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:49:34Z","timestamp":1772556574320,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI, Japan","doi-asserted-by":"publisher","award":["JP22H03596"],"award-info":[{"award-number":["JP22H03596"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3480977","type":"journal-article","created":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T17:25:18Z","timestamp":1729013118000},"page":"155773-155788","source":"Crossref","is-referenced-by-count":5,"title":["A Cost-Efficient FPGA-Based CNN-Transformer Using Neural ODE"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2654-5823","authenticated-orcid":false,"given":"Ikumi","family":"Okubo","sequence":"first","affiliation":[{"name":"Graduate School of Science and Technology, Keio University, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8534-2381","authenticated-orcid":false,"given":"Keisuke","family":"Sugiura","sequence":"additional","affiliation":[{"name":"Graduate School of Science and Technology, Keio University, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9578-3842","authenticated-orcid":false,"given":"Hiroki","family":"Matsutani","sequence":"additional","affiliation":[{"name":"Graduate School of Science and Technology, Keio University, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref7","article-title":"Patches are all you need?","author":"Trockman","year":"2022","journal-title":"arXiv:2201.09792"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref9","first-page":"1","article-title":"How do vision transformers work?","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Park"},{"key":"ref10","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","author":"Dai","year":"2021","journal-title":"arXiv:2106.04803"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","first-page":"6571","article-title":"Neural ordinary differential equations","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW59300.2023.00029"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.irbm.2020.07.001"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48084\/etasr.4613"},{"key":"ref16","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25111"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00119"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-023-00842-9"},{"key":"ref21","first-page":"1","article-title":"Reformer: The efficient transformer","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Kitaev"},{"key":"ref22","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref23","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref24","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Dao"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","article-title":"Neural SDE: Stabilizing neural ODE networks with stochastic noise","author":"Liu","year":"2019","journal-title":"arXiv:1906.02355"},{"key":"ref27","first-page":"3154","article-title":"How to train your neural ODE: The world of Jacobian and kinetic regularization","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Finlay"},{"key":"ref28","article-title":"On robustness of neural ordinary differential equations","author":"Yan","year":"2019","journal-title":"arXiv:1910.05513"},{"key":"ref29","first-page":"3140","article-title":"Augmented neural ODEs","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Dupont"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED51717.2021.9424344"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref32","article-title":"VAQF: Fully automatic software-hardware co-design framework for low-bit vision transformer","author":"Sun","year":"2022","journal-title":"arXiv:2201.06618"},{"key":"ref33","article-title":"ME-ViT: A single-load memory-efficient FPGA accelerator for vision transformers","author":"Marino","year":"2024","journal-title":"arXiv:2402.09709"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT51360.2021.9596007"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2023.3333756"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01210"},{"key":"ref37","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Simonyan"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/PDP55904.2022.00031"},{"key":"ref40","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref42","first-page":"3286","article-title":"Atention augmented convolutional networks","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Zoph"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.523"},{"key":"ref44","first-page":"12360","article-title":"Root mean square layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhang"},{"key":"ref45","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref46","first-page":"10096","article-title":"EfficientNetv2: Smaller models and faster training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICBAIE52039.2021.9389905"},{"key":"ref49","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Coates"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10717866.pdf?arnumber=10717866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:55:21Z","timestamp":1732668921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10717866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3480977","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}