{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:57:52Z","timestamp":1780675072537,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4500200"],"award-info":[{"award-number":["2022YFB4500200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62374108"],"award-info":[{"award-number":["62374108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3656516","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:27:22Z","timestamp":1731007642000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["QUQ: Quadruplet Uniform Quantization for Efficient Vision Transformer Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3673-237X","authenticated-orcid":false,"given":"Xinkuang","family":"Geng","sequence":"first","affiliation":[{"name":"Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0505-8183","authenticated-orcid":false,"given":"Siting","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7548-4116","authenticated-orcid":false,"given":"Leibo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits and The National Lab for Information Science and Technology, Tsinghua University, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8849-4994","authenticated-orcid":false,"given":"Jie","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3705-4240","authenticated-orcid":false,"given":"Honglan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547826"},{"key":"e_1_3_2_1_3_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16\u00d716 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317783"},{"key":"e_1_3_2_1_5_1","volume-title":"International conference on machine learning. PMLR, 5506--5518","author":"Kim Sehoon","year":"2021","unstructured":"Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W Mahoney, and Kurt Keutzer. 2021. I-bert: Integer-only bert quantization. In International conference on machine learning. PMLR, 5506--5518."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"e_1_3_2_1_7_1","volume-title":"Fq-vit: Post-training quantization for fully quantized vision transformer. arXiv preprint arXiv:2111.13824","author":"Lin Yang","year":"2021","unstructured":"Yang Lin, Tianyu Zhang, Peiqin Sun, Zheng Li, and Shuchang Zhou. 2021. Fq-vit: Post-training quantization for fully quantized vision transformer. arXiv preprint arXiv:2111.13824 (2021)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_9_1","volume-title":"Yelysei Bondarenko, Mart Van Baalen, and Tijmen Blankevoort.","author":"Nagel Markus","year":"2021","unstructured":"Markus Nagel, Marios Fournarakis, Rana Ali Amjad, Yelysei Bondarenko, Mart Van Baalen, and Tijmen Blankevoort. 2021. A white paper on neural network quantization. arXiv preprint arXiv:2106.08295 (2021)."},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. PMLR, 10347--10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347--10357."},{"key":"e_1_3_2_1_11_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_12"}],"event":{"name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","location":"San Francisco CA USA","acronym":"DAC '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656516","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3656516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:55Z","timestamp":1750295875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":12,"alternative-id":["10.1145\/3649329.3656516","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3656516","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}