{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T16:07:52Z","timestamp":1788019672447,"version":"build-2784847793"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4400600"],"award-info":[{"award-number":["2022YFB4400600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["2023A007"],"award-info":[{"award-number":["2023A007"]}]},{"DOI":"10.13039\/501100013064","name":"Postgraduate Research and Practice Innovation Program of Jiangsu Province","doi-asserted-by":"publisher","award":["2023A007"],"award-info":[{"award-number":["2023A007"]}],"id":[{"id":"10.13039\/501100013064","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013064","name":"Postgraduate Research and Practice Innovation Program of Jiangsu Province","doi-asserted-by":"publisher","award":["KYCX24_0149"],"award-info":[{"award-number":["KYCX24_0149"]}],"id":[{"id":"10.13039\/501100013064","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. I"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tcsi.2024.3485192","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T13:42:20Z","timestamp":1730727740000},"page":"1296-1307","source":"Crossref","is-referenced-by-count":13,"title":["Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7845-0154","authenticated-orcid":false,"given":"Huihong","family":"Shi","sequence":"first","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6965-3436","authenticated-orcid":false,"given":"Haikuo","family":"Shao","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wendong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7227-4786","authenticated-orcid":false,"given":"Zhongfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, 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","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"OpenAI","year":"2023"},{"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":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref6","article-title":"BRECQ: Pushing the limit of post-training quantization by block reconstruction","author":"Li","year":"2021","journal-title":"arXiv:2102.05426"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref8","first-page":"11875","article-title":"HAWQ-v3: Dyadic neural network quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yao"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2024.3422684"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/164"},{"key":"ref11","article-title":"PTQ4 ViT: Post-training quantization for vision transformers with twin uniform quantization","author":"Yuan","year":"2021","journal-title":"arXiv:2111.12293"},{"key":"ref12","article-title":"I-ViT: Integer-only quantization for efficient vision transformer inference","author":"Li","year":"2022","journal-title":"arXiv:2207.01405"},{"key":"ref13","first-page":"17302","article-title":"EfficientViT: Enhanced linear attention for high-resolution low-computation visual recognition","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Cai"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01387"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00027"},{"key":"ref18","article-title":"ViTCoD: Vision transformer acceleration via dedicated algorithm and accelerator co-design","author":"You","year":"2022","journal-title":"arXiv:2210.09573"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref20","first-page":"8815","article-title":"Q-BERT: Hessian based ultra low precision quantization of BERT","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Shen"},{"key":"ref21","first-page":"28092","article-title":"Post-training quantization for vision transformer","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref22","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","author":"Xiao","year":"2022","journal-title":"arXiv:2211.10438"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref24","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref28","article-title":"ViTALiTy: Unifying low-rank and sparse approximation for vision transformer acceleration with a linear Taylor attention","author":"Dass","year":"2022","journal-title":"arXiv:2211.05109"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref31","first-page":"1","article-title":"WSQ-AdderNet: Efficient weight standardization based quantized AdderNet FPGA accelerator design with high-density INT8 DSP-LUT co-packing optimization","volume-title":"Proc. IEEE\/ACM Int. Conf. Comput. Aided Design (ICCAD)","author":"Zhang"},{"key":"ref32","article-title":"Up or down? Adaptive rounding for post-training quantization","author":"Nagel","year":"2020","journal-title":"arXiv:2004.10568"},{"key":"ref33","article-title":"Learned step size quantization","author":"Esser","year":"2019","journal-title":"arXiv:1902.08153"},{"key":"ref34","article-title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","author":"Wei","year":"2023","journal-title":"arXiv:2304.09145"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375311"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055240"},{"key":"ref37","article-title":"Full stack optimization of transformer inference: A survey","author":"Kim","year":"2023","journal-title":"arXiv:2302.14017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00292"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"ref41","first-page":"9847","article-title":"Towards accurate post-training network quantization via bit-split and stitching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref42","article-title":"EasyQuant: Post-training quantization via scale optimization","author":"Wu","year":"2020","journal-title":"arXiv:2006.16669"},{"key":"ref43","volume-title":"Fastertransformer","year":"2022"},{"key":"ref44","article-title":"I-BERT: Integer-only BERT quantization","author":"Kim","year":"2021","journal-title":"arXiv:2101.01321"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3312775"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3197489"},{"key":"ref47","volume-title":"Wp486: Deep learning with int8 optimization on Xilinx devices","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"}],"container-title":["IEEE Transactions on Circuits and Systems I: Regular Papers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8919\/10905058\/10742120.pdf?arnumber=10742120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T19:54:04Z","timestamp":1774641244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10742120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":49,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsi.2024.3485192","relation":{},"ISSN":["1549-8328","1558-0806"],"issn-type":[{"value":"1549-8328","type":"print"},{"value":"1558-0806","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}