{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:19:48Z","timestamp":1762341588959,"version":"3.37.3"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) Grant funded by the Korean Government (MSIT)","award":["2020-0-01305"],"award-info":[{"award-number":["2020-0-01305"]}]},{"DOI":"10.13039\/501100003725","name":"Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education","doi-asserted-by":"publisher","award":["NRF-2019R1A6A1A03032119"],"award-info":[{"award-number":["NRF-2019R1A6A1A03032119"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3054879","type":"journal-article","created":{"date-parts":[[2021,1,27]],"date-time":"2021-01-27T20:48:43Z","timestamp":1611780523000},"page":"20828-20839","source":"Crossref","is-referenced-by-count":62,"title":["Zero-Centered Fixed-Point Quantization With Iterative Retraining for Deep Convolutional Neural Network-Based Object Detectors"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5030-5561","authenticated-orcid":false,"given":"Sungrae","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7962-657X","authenticated-orcid":false,"given":"Hyun","family":"Kim","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Convolutional neural networks using logarithmic data representation","author":"miyashita","year":"2016","journal-title":"arXiv 1603 01025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.114"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3003518"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CANDARW.2019.00032"},{"key":"ref37","article-title":"Deep convolutional neural network inference with floating-point weights and fixed-point activations","author":"lai","year":"2017","journal-title":"arXiv 1703 03073"},{"key":"ref36","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref10","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICET49382.2020.9119500"},{"key":"ref11","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"bochkovskiy","year":"2020","journal-title":"arXiv 2004 10934"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2705069"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS48895.2020.9073907"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3289185"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2019.2962516"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2018.8351021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990087"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2020.3015753"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00059"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00452"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2019.2905242"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2857080"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622396"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref7","article-title":"Layer-specific optimization for mixed data flow with mixed precision in FPGA design for CNN-based object detectors","author":"nguyen","year":"2020","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"1","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref9","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2949857"},{"key":"ref22","first-page":"7948","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","author":"banner","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref23","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015","journal-title":"arXiv 1510 00149 [cs]"},{"key":"ref41","article-title":"Bit efficient quantization for deep neural networks","author":"nayak","year":"2019","journal-title":"arXiv 1910 04877"},{"key":"ref26","first-page":"2849","article-title":"Fixed point quantization of deep convolutional networks","author":"lin","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref25","first-page":"1","article-title":"Learning multimodal fixed-point weights using gradient descent","author":"enderich","year":"2019","journal-title":"Proc 27th Eur Symp Artif Neural Netw Comput Intell Mach Learn"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09336635.pdf?arnumber=9336635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T14:24:41Z","timestamp":1643207081000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9336635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3054879","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}