{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T23:47:53Z","timestamp":1793317673912,"version":"4.5.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","funder":[{"name":"EU Horizon 2020 Research and Innovation projects OPRECOMP","award":["732631"],"award-info":[{"award-number":["732631"]}]},{"name":"WiPLASH","award":["863337"],"award-info":[{"award-number":["863337"]}]},{"name":"Artificial Intelligence for Digital Industry","award":["826060"],"award-info":[{"award-number":["826060"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2021,8,1]]},"DOI":"10.1109\/tc.2021.3066883","type":"journal-article","created":{"date-parts":[[2021,3,18]],"date-time":"2021-03-18T15:48:31Z","timestamp":1616082511000},"page":"1253-1268","source":"Crossref","is-referenced-by-count":123,"title":["DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6215-8220","authenticated-orcid":false,"given":"Alessio","family":"Burrello","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7495-6895","authenticated-orcid":false,"given":"Angelo","family":"Garofalo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nazareno","family":"Bruschi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9221-4633","authenticated-orcid":false,"given":"Giuseppe","family":"Tagliavini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0651-5393","authenticated-orcid":false,"given":"Davide","family":"Rossi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7924-933X","authenticated-orcid":false,"given":"Francesco","family":"Conti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Tensorflow lite for microcontrollers","author":"abadi","year":"2015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2017.2654506"},{"key":"ref33","article-title":"MCUNet: Tiny deep learning on IoT devices","author":"lin","year":"2020"},{"key":"ref32","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref30","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CODESISSS.2018.8525915"},{"key":"ref36","article-title":"CMSIS-NN: Efficient neural network kernels for arm Cortex-M CPUs","author":"lai","year":"2018"},{"key":"ref35","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"choi","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.2983648"},{"key":"ref10","first-page":"683","article-title":"A ultra-low-energy convolution engine for fast brain-inspired vision in multicore clusters","author":"conti","year":"2015","journal-title":"Proc Des Autom Test Eur Conf Exhib"},{"key":"ref40","article-title":"Technical Report: NEMO DNN quantization for deployment model","author":"conti","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CICC.2017.7993626"},{"key":"ref12","first-page":"186","article-title":"XpulpNN: Accelerating quantized neural networks on RISC-V processors through ISA extensions","author":"garofalo","year":"2020","journal-title":"Proc Des Autom Test Eur Conf"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870349"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0155"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-015-1070-9"},{"key":"ref16","article-title":"Cypress DRAM","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2013.04.006"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MCSoC.2015.45"},{"key":"ref19","first-page":"89","article-title":"Optimal tiling strategy for memory bandwidth reduction for CNNs","author":"cecconi","year":"2017","journal-title":"Proc Int Conf Adv Concepts Intell Vis Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2844296"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378514"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TBCAS.2019.2959160"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2017.2698019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01746"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2917066"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00103"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-18338-7_19"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600587CM"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2017.10.002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2013.6657019"},{"key":"ref45","first-page":"1","article-title":"$\\mu$?DMA: An autonomous I\/O subsystem for IoT end-nodes","author":"pullini","year":"2017","journal-title":"Proc 27th Int Symp Power Timing Model Optim Simul"},{"key":"ref22","article-title":"X-CUBE-AI","year":"2017"},{"key":"ref21","article-title":"TensorFlow lite micro: Embedded machine learning on TinyML systems","author":"david","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2912307"},{"key":"ref24","article-title":"Data movement is all you need: A case study of transformer networks","author":"ivanov","year":"2020"},{"key":"ref41","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2018.8445101"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2597917.2597922"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2985963"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2011.5763085"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3358198"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/9478065\/09381618.pdf?arnumber=9381618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T16:59:24Z","timestamp":1643389164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9381618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,1]]},"references-count":45,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tc.2021.3066883","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,1]]}}}