{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T13:05:25Z","timestamp":1754399125542,"version":"3.37.3"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004405","name":"Toyota Motor Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004405","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/jstsp.2020.2966331","type":"journal-article","created":{"date-parts":[[2020,1,13]],"date-time":"2020-01-13T20:48:00Z","timestamp":1578948480000},"page":"634-645","source":"Crossref","is-referenced-by-count":12,"title":["A 1.15-TOPS 6.57-TOPS\/W Neural Network Processor for Multi-Scale Object Detection With Reduced Convolutional Operations"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7029-695X","authenticated-orcid":false,"given":"Reiya","family":"Kawamoto","sequence":"first","affiliation":[]},{"given":"Masakazu","family":"Taichi","sequence":"additional","affiliation":[]},{"given":"Masaya","family":"Kabuto","sequence":"additional","affiliation":[]},{"given":"Daisuke","family":"Watanabe","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8336-2220","authenticated-orcid":false,"given":"Shintaro","family":"Izumi","sequence":"additional","affiliation":[]},{"given":"Masahiko","family":"Yoshimoto","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8677-4733","authenticated-orcid":false,"given":"Hiroshi","family":"Kawaguchi","sequence":"additional","affiliation":[]},{"given":"Go","family":"Matsukawa","sequence":"additional","affiliation":[]},{"given":"Toshio","family":"Goto","sequence":"additional","affiliation":[]},{"given":"Motoshi","family":"Kojima","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"26","article-title":"Going deeper with embedded FPGA platform for convolutional neural network","author":"qiu","year":"2016","journal-title":"Proc ACM\/SIGDA Int Symp Field-Programmable Gate Arrays"},{"key":"ref38","first-page":"71","article-title":"Accelerating convolutional neural networks using low precision arithmetic","author":"naganuma","year":"2018","journal-title":"Proc Int Conf High Perform Comput Asia–Pacific Region"},{"key":"ref33","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref32","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"ref37","first-page":"409","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"year":"0","key":"ref36"},{"year":"0","key":"ref35"},{"year":"2012","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"year":"0","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870350"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870353"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/VLSIC.2017.8008533"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/VLSIC.2017.8008534"},{"key":"ref17","first-page":"216","article-title":"QUEST: A 7.49 TOPS multi-purpose log-quantized DNN inference engine stacked on 96\ufffdMB 3D SRAM using inductive-coupling technology in 40 nm CMOS","author":"ueyoshi","year":"2018","journal-title":"Proc Int Solid-State Circuits Conf"},{"key":"ref18","first-page":"218","article-title":"UNPU: A 50.6 TOPS\/W unified deep neural network accelerator with 1b-to16b fully variable weight bit-precision","author":"lee","year":"2018","journal-title":"Proc Int Solid-State Circuits Conf"},{"key":"ref19","first-page":"222","article-title":"An always-on 3.8 ?J\/86% CIFAR-10 mixed-signal binary CNN processor with all memory on chip in 28 nm CMOS","author":"bankman","year":"2018","journal-title":"Proc Int Solid-State Circuits Conf"},{"key":"ref28","first-page":"134","article-title":"An 879GOPS 243 mW 80 fps VGA fully visual CNN-SLAM processor for wide-range autonomous exploration","author":"li","year":"2019","journal-title":"Proc Int Solid-State Circuits Conf"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref27","first-page":"130","article-title":"An 11.5TOPS\/W 1024-MAC butterfly structure deal-core sparsity-aware neural processing unit in 8 nm flagship mobile SoC","author":"song","year":"2019","journal-title":"Proc Int Solid-State Circuits Conf"},{"key":"ref3","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.106"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"article-title":"DSSD: Deconvolutional single shot detector","year":"2017","author":"fu","key":"ref8"},{"key":"ref7","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"article-title":"FSSD: Feature fusion single shot multibox detector","year":"2017","author":"li","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310397"},{"key":"ref22","first-page":"37","article-title":"An ultra-high energy-efficient reconfigurable processor for deep neural networks with binary\/ternary weights in 28 nm CMOS","author":"yin","year":"2018","journal-title":"Proc Symp Very Large Scale Integr Circuits"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIC.2018.8502404"},{"key":"ref42","first-page":"161","article-title":"Optimizing FPGA-based accelerator design for deep convolutional neural networks","author":"zhang","year":"2015","journal-title":"Proc ACM\/SIGDA Int Symp Field-Programmable Gate Arrays"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIC.2018.8502266"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196129"},{"key":"ref23","first-page":"39","article-title":"2.9 TOPS\/W reconfigurable dense\/sparse matrix-multiply accelerator with unified INT8\/INT16\/FP16 Datapath in 14 nm Tri-gate CMOS","author":"anders","year":"2018","journal-title":"Proc Symp Very Large Scale Integr Circuits"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIC.2018.8502421"},{"key":"ref25","first-page":"139","article-title":"A 141 uW, 2.46 pJ\/Neuron binarized convolutional neural network based self-learning speech recognition processor in 28 nm CMOS","author":"yin","year":"2018","journal-title":"Proc Symp Very Large Scale Integr Circuits"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9163420\/08957468.pdf?arnumber=8957468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:08:25Z","timestamp":1651079305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8957468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":42,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2020.2966331","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"type":"print","value":"1932-4553"},{"type":"electronic","value":"1941-0484"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}