{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:22:26Z","timestamp":1781022146246,"version":"3.54.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"22","license":[{"start":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:00:00Z","timestamp":1731628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:00:00Z","timestamp":1731628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:00:00Z","timestamp":1731628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute of Information and Communications Technology Planning and Evaluation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea Government","award":["RS-2023-00277060"],"award-info":[{"award-number":["RS-2023-00277060"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2024,11,15]]},"DOI":"10.1109\/jiot.2024.3403844","type":"journal-article","created":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T17:27:51Z","timestamp":1716312471000},"page":"36384-36396","source":"Crossref","is-referenced-by-count":9,"title":["Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers With Bridge Block Reconstruction for IoT Systems"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9332-3508","authenticated-orcid":false,"given":"Jemin","family":"Lee","sequence":"first","affiliation":[{"name":"Artificial Intelligence Computing Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2973-246X","authenticated-orcid":false,"given":"Yongin","family":"Kwon","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Computing Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8244-4817","authenticated-orcid":false,"given":"Sihyeong","family":"Park","sequence":"additional","affiliation":[{"name":"SoC Platform Research Center, Korea Electronics Technology Institute, Seongnam, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7319-1053","authenticated-orcid":false,"given":"Misun","family":"Yu","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Computing Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9524-0738","authenticated-orcid":false,"given":"Jeman","family":"Park","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Computing Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1105-0818","authenticated-orcid":false,"given":"Hwanjun","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3296493"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3213650"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3290818"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref6","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref7","article-title":"Separable self-attention for mobile vision transformers","author":"Mehta","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref8","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","author":"Krishnamoorthi","year":"2018","journal-title":"arXiv:1806.08342"},{"key":"ref9","first-page":"1","article-title":"Learned step size quantization","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Esser"},{"key":"ref10","first-page":"1","article-title":"Pact: Parameterized clipping activation for quantized neural networks","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Choi"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref13","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv:1606.06160"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref15","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Han"},{"key":"ref16","article-title":"Automated backend-aware post-training quantization","author":"Jiang","year":"2021","journal-title":"arXiv:2103.14949"},{"key":"ref17","first-page":"1","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst.","volume":"32","author":"Banner"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"ref19","first-page":"7543","article-title":"Improving neural network quantization without retraining using outlier channel splitting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao"},{"key":"ref20","article-title":"Quantization for rapid deployment of deep neural networks","author":"Lee","year":"2018","journal-title":"arXiv:1810.05488"},{"issue":"9","key":"ref21","first-page":"495","article-title":"Fast adjustable threshold for uniform neural network quantization","volume":"13","author":"Goncharenko","year":"2019","journal-title":"Int. J. Comput. Inf. Eng."},{"issue":"4","key":"ref22","first-page":"5","article-title":"8-bit inference with tensorrt","volume-title":"Proc. GPU Technol. Conf.","volume":"2","author":"Migacz"},{"key":"ref23","article-title":"Integer quantization for deep learning inference: Principles and empirical evaluation","author":"Wu","year":"2020","journal-title":"arXiv:2004.09602"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref25","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref27","article-title":"EasyQuant: Post-training quantization via scale optimization","author":"Wu","year":"2020","journal-title":"arXiv:2006.16669"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/164"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01580"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"ref32","first-page":"12934","article-title":"EfficientFormer: Vision transformers at mobileNet speed","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref35","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"ref41","first-page":"4486","article-title":"Same, same but different: Recovering neural network quantization error through weight factorization","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Meller"},{"key":"ref42","first-page":"7197","article-title":"Up or down? Adaptive rounding for post-training quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nagel"},{"key":"ref43","article-title":"BRECQ: Pushing the limit of post-training quantization by block reconstruction","author":"Li","year":"2021","journal-title":"arXiv:2102.05426"},{"key":"ref44","first-page":"4466","article-title":"Accurate post training quantization with small calibration sets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hubara"},{"key":"ref45","article-title":"QDrop: randomly dropping quantization for extremely low-bit post-training quantization","author":"Wei","year":"2022","journal-title":"arXiv:2203.05740"},{"key":"ref46","first-page":"1","article-title":"Leveraging inter-layer dependency for post-training quantization","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref47","first-page":"28092","article-title":"Post-training quantization for vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547826"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01946"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00292"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3277869"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3111723"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10747044\/10536014.pdf?arnumber=10536014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T19:05:24Z","timestamp":1738004724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10536014\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,15]]},"references-count":52,"journal-issue":{"issue":"22"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2024.3403844","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,15]]}}}