{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:26:26Z","timestamp":1759335986672,"version":"3.37.3"},"reference-count":47,"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":"Ministry of Trade, Industry, and Energy (MOTIE), South Korea, through the Technology Innovation Program or the Industrial Strategic Technology Development Program","award":["10085646"],"award-info":[{"award-number":["10085646"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3077596","type":"journal-article","created":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T21:08:45Z","timestamp":1620248925000},"page":"69601-69608","source":"Crossref","is-referenced-by-count":5,"title":["Compressing Neural Networks With Inter Prediction and Linear Transformation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4379-2303","authenticated-orcid":false,"given":"Kang-Ho","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2677-3186","authenticated-orcid":false,"given":"Sung-Ho","family":"Bae","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"6869","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"hubara","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref38","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or ?1","author":"courbariaux","year":"2016","journal-title":"arXiv 1602 02830 [cs]"},{"key":"ref33","first-page":"2849","article-title":"Fixed point quantization of deep convolutional networks","author":"lin","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref37","first-page":"3123","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"Improving neural network quantization without retraining using outlier channel splitting","author":"zhao","year":"2019","journal-title":"arXiv 1901 09504"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00826"},{"key":"ref34","article-title":"Resiliency of deep neural networks under quantization","author":"sung","year":"2015","journal-title":"arXiv 1511 06488"},{"key":"ref10","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","author":"hassibi","year":"1993","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01461"},{"key":"ref11","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","author":"han","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","article-title":"Pruning filters for efficient ConvNets","author":"li","year":"2016","journal-title":"arXiv 1608 08710"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1117\/12.20700"},{"key":"ref14","article-title":"Compressing deep convolutional networks using vector quantization","author":"gong","year":"2014","journal-title":"arXiv 1412 6115"},{"key":"ref15","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":"ref16","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00529"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802998"},{"key":"ref4","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","article-title":"And the bit goes down: Revisiting the quantization of neural networks","author":"stock","year":"2019","journal-title":"arXiv 1907 05686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1109\/TCSVT.2003.815165","article-title":"overview of the h.264\/avc video coding standard","volume":"13","author":"wiegand","year":"2003","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref2","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","first-page":"598","article-title":"Optimal brain damage","author":"lecun","year":"1990","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","first-page":"396","article-title":"Handwritten digit recognition with a back-propagation network","author":"lecun","year":"1990","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref20","article-title":"Neural epitome search for architecture-agnostic network compression","author":"zhou","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"article-title":"Experimental design and analysis","year":"2012","author":"seltman","key":"ref45"},{"key":"ref22","first-page":"22","article-title":"Global weight: Network level weight sharing for compression of deep neural network","author":"shin","year":"2020","journal-title":"Proc Korean Soc Broadcast Eng Conf"},{"key":"ref47","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","article-title":"FSNet: Compression of deep convolutional neural networks by filter summary","author":"yang","year":"2019","journal-title":"arXiv 1902 03264"},{"key":"ref42","first-page":"253","article-title":"CNNpack: Packing convolutional neural networks in the frequency domain","author":"wang","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/35.556485"},{"key":"ref23","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-374388-6.00003-X"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2017.7926982"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09423992.pdf?arnumber=9423992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:57Z","timestamp":1639770957000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9423992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3077596","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}