{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T12:02:12Z","timestamp":1786449732669,"version":"3.56.0"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&#x0026;D Program of China","award":["2023YFB3002002"],"award-info":[{"award-number":["2023YFB3002002"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322213"],"award-info":[{"award-number":["62322213"]}],"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":["62461146205"],"award-info":[{"award-number":["62461146205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20230484397"],"award-info":[{"award-number":["20230484397"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20220484137"],"award-info":[{"award-number":["20220484137"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Laboratory of Computer Architecture","award":["CLQ202414"],"award-info":[{"award-number":["CLQ202414"]}]},{"name":"State Key Laboratory of Computer Architecture","award":["CCF-Aliyun2024003"],"award-info":[{"award-number":["CCF-Aliyun2024003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cloud Comput."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tcc.2025.3559346","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T17:55:59Z","timestamp":1744221359000},"page":"694-710","source":"Crossref","is-referenced-by-count":68,"title":["Breaking the Edge: Enabling Efficient Neural Network Inference on Integrated Edge Devices"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1983-7321","authenticated-orcid":false,"given":"Feng","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Data Engineering and Knowledge Engineering (MOE), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7538-9722","authenticated-orcid":false,"given":"Jiawei","family":"Guan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Data Engineering and Knowledge Engineering (MOE), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1824-1898","authenticated-orcid":false,"given":"Qiangjun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Data Engineering and Knowledge Engineering (MOE), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0863-1820","authenticated-orcid":false,"given":"Kuangyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California, Riverside, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1857-1368","authenticated-orcid":false,"given":"Xiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Data Engineering and Knowledge Engineering (MOE), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8618-4581","authenticated-orcid":false,"given":"Bingsheng","family":"He","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7656-6428","authenticated-orcid":false,"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5757-9135","authenticated-orcid":false,"given":"Xiaoyong","family":"Du","sequence":"additional","affiliation":[{"name":"Key Laboratory of Data Engineering and Knowledge Engineering (MOE), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2024.3361858"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2021.3109385"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2024.3362355"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3201544"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3215520"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2023.3234543"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2023.3285654"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2970118"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.bushor.2015.03.008"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2021.3107022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3175725"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3177649"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2023.3258982"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2020.2997008"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-019-01241-7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2944889"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3727\/109830511X12978702284390"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2999572.2999604"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2522"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2019.10.012"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref23","article-title":"An empirical evaluation of deep learning on highway driving","author":"Huval","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3218813"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2586074"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3046870"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.16"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2017.05.001"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/NAS.2015.7255222"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2637166.2637229"},{"key":"ref35","first-page":"1","article-title":"Efficient deep learning inference on edge devices","volume-title":"Proc. Conf. Syst. Mach. Learn.","author":"Jiang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/EMC249363.2019.00013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015676"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.3023723"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3059108"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00096"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/S1352-2310(97)00447-0"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref47","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref48","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref49","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size","author":"Iandola","year":"2016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415493"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476302"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-010-0105-z"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27146-0_9"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2809695.2823464"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-020-0428-6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2019.05.008"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09994-0"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2018.5796"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376714"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3462462.3468880"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3212804"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2013.6574660"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196928"},{"key":"ref66","article-title":"Unified memory in CUDA 6.0. A brief overview of related data access and transfer issues","author":"Negrut","year":"2014"},{"key":"ref67","volume-title":"CUDA by Example: An Introduction to General-Purpose GPU Programming","author":"Sanders","year":"2010"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/Cluster48925.2021.00020"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2017.120"},{"key":"ref70","first-page":"633","article-title":"FineStream: Fine-grained window-based stream processing on CPU-GPU integrated architectures","volume-title":"Proc. 2020 USENIX Annu. Tech. Conf.","author":"Zhang"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/PDP55904.2022.00014"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/99.660313"},{"key":"ref73","first-page":"304","article-title":"Laconic deep learning inference acceleration","volume-title":"Proc. 46th Int. Symp. Comput. Archit.","author":"Sharify"},{"key":"ref74","first-page":"264","article-title":"TIE: Energy-efficient tensor train-based inference engine for deep neural network","volume-title":"Proc. 46th Int. Symp. Comput. Archit.","author":"Deng"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080244"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001165"},{"key":"ref78","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3390\/sym11010001"},{"key":"ref80","article-title":"Deep convolutional neural network for age estimation based on VGG-face model","author":"Qawaqneh","year":"2017"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.4108\/eai.27-8-2020.2294291"},{"key":"ref85","article-title":"asingh33\/CNNGestureRecognizer: CNNGestureRecognizer","author":"Singh","year":"2017"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.109"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3503047.3503153"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/9847249"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3079337"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/7562167"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.entcom.2021.100404"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350958"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.3390\/s20102972"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2943405"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3218527"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2024.3353176"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-2791-8"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1186\/s13677-021-00250-w"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.3390\/sym14122554"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2023.108760"},{"key":"ref101","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref104","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358263"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3093234"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00148"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3119402"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/3243176.3243210"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2017.19"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2014.7116910"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6245519\/11027456\/10959707.pdf?arnumber=10959707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:24:34Z","timestamp":1749270274000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10959707\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":100,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2025.3559346","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"value":"2168-7161","type":"electronic"},{"value":"2372-0018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}