{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T03:09:59Z","timestamp":1782788999307,"version":"3.54.5"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Scientific and Technological Innovation 2030 of China","award":["2021ZD0114401"],"award-info":[{"award-number":["2021ZD0114401"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62104175"],"award-info":[{"award-number":["62104175"]}],"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":["U22A2013"],"award-info":[{"award-number":["U22A2013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3439600","type":"journal-article","created":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T18:29:23Z","timestamp":1722968963000},"page":"13596-13610","source":"Crossref","is-referenced-by-count":14,"title":["A 109-GOPs\/W FPGA-Based Vision Transformer Accelerator With Weight-Loop Dataflow Featuring Data Reusing and Resource Saving"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1956-766X","authenticated-orcid":false,"given":"Yueqi","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7685-2141","authenticated-orcid":false,"given":"Lichen","family":"Feng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongwei","family":"Shan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7764-1928","authenticated-orcid":false,"given":"Zhangming","family":"Zhu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"issue":"8","key":"ref3","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref4","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":"ref5","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Han"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277462"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222906"},{"key":"ref12","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248271"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3386779"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3274964"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3020569"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071047"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00027"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9474043"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3477002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3197489"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MC.1982.1653825"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3178474"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3312775"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2022.3196055"},{"key":"ref30","first-page":"20","volume-title":"8-bit dot-product acceleration","author":"Fu","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2824280"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICECS49266.2020.9294850"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/A-SSCC53895.2021.9634838"},{"key":"ref34","article-title":"FQ-ViT: Post-training quantization for fully quantized vision transformer","author":"Lin","year":"2021","journal-title":"arXiv:2111.13824"},{"key":"ref35","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811783\/10623817.pdf?arnumber=10623817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:23:00Z","timestamp":1736972580000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10623817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":35,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3439600","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}