{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:32:14Z","timestamp":1783438334242,"version":"3.54.6"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U1908209"],"award-info":[{"award-number":["U1908209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61632001"],"award-info":[{"award-number":["61632001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0101400"],"award-info":[{"award-number":["2018AAA0101400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1109\/tcsvt.2020.3013170","type":"journal-article","created":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T20:37:26Z","timestamp":1596141446000},"page":"2008-2019","source":"Crossref","is-referenced-by-count":24,"title":["SASL: Saliency-Adaptive Sparsity Learning for Neural Network Acceleration"],"prefix":"10.1109","volume":"31","author":[{"given":"Jun","family":"Shi","sequence":"first","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Xu","sequence":"additional","affiliation":[{"name":"KDDI Research, Inc., Fujimino, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuyuki","family":"Tasaka","sequence":"additional","affiliation":[{"name":"KDDI Research, Inc., Fujimino, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8525-5066","authenticated-orcid":false,"given":"Zhibo","family":"Chen","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Pruning filters for efficient ConvNets","author":"li","year":"2016","journal-title":"arXiv 1608 08710"},{"key":"ref38","first-page":"6379","article-title":"Global sparse momentum SGD for pruning very deep neural networks","author":"ding","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","first-page":"2498","article-title":"Variational dropout sparsifies deep neural networks","volume":"70","author":"molchanov","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref32","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":"ref31","first-page":"598","article-title":"Optimal brain damage","author":"lecun","year":"1990","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00171"},{"key":"ref37","first-page":"4933","article-title":"One ticket to win them all: Generalizing lottery ticket initializations across datasets and optimizers","author":"morcos","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"frankle","year":"2018","journal-title":"arXiv 1803 03635"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2911674"},{"key":"ref34","article-title":"Designing neural network architectures using reinforcement learning","author":"baker","year":"2016","journal-title":"arXiv 1611 02167"},{"key":"ref60","first-page":"875","article-title":"Discrimination-aware channel pruning for deep neural networks","author":"zhuang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00508"},{"key":"ref63","author":"lecun","year":"2015","journal-title":"Lenet-5 convolutional neural networks"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00290"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2885972"},{"key":"ref29","article-title":"DeepHoyer: Learning sparser neural network with differentiable scale-invariant sparsity measures","author":"yang","year":"2019","journal-title":"arXiv 1908 09979"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2950105"},{"key":"ref22","first-page":"7242","article-title":"Trimming the $\\ell_{1}$\n regularizer: Statistical analysis, optimization, and applications to deep learning","author":"yun","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2019.2908729"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2906563"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00721"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00932"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852463"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00339"},{"key":"ref51","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/336"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref57","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":"ref56","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref55","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref53","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc NeurIPS Autodiff Workshop"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref40","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"hu","year":"2016","journal-title":"arXiv 1607 03250"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_40"},{"key":"ref13","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2748585"},{"key":"ref16","article-title":"Learning sparse neural networks through $L_{0}$\n regularization","author":"louizos","year":"2017","journal-title":"arXiv 1712 01312"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2785403"},{"key":"ref18","first-page":"1","article-title":"Auto-balanced filter pruning for efficient convolutional neural networks","author":"ding","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"ref4","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"chen","year":"2014","journal-title":"arXiv 1412 7062"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00289"},{"key":"ref9","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2016","journal-title":"arXiv 1611 03530"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00083"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref43","article-title":"Layer-compensated pruning for resource-constrained convolutional neural networks","author":"chin","year":"2018","journal-title":"arXiv 1810 00518"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9423778\/09153007.pdf?arnumber=9153007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:45:39Z","timestamp":1781639139000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9153007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":63,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.3013170","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5]]}}}