{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T18:01:58Z","timestamp":1773511318984,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tnnls.2021.3117685","type":"journal-article","created":{"date-parts":[[2021,11,30]],"date-time":"2021-11-30T23:27:41Z","timestamp":1638314861000},"page":"4440-4450","source":"Crossref","is-referenced-by-count":13,"title":["LRPRNet: Lightweight Deep Network by Low-Rank Pointwise Residual Convolution"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9239-0402","authenticated-orcid":false,"given":"Bin","family":"Sun","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5845-8602","authenticated-orcid":false,"given":"Jun","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7686-8784","authenticated-orcid":false,"given":"Ming","family":"Shao","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, University of Massachusetts Dartmouth, Dartmouth, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5098-2853","authenticated-orcid":false,"given":"Yun","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1995.1004"},{"key":"ref57","article-title":"IGCV3: Interleaved low-rank group convolutions for efficient deep neural networks","author":"sun","year":"2018","journal-title":"arXiv 1806 00178"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"ref56","first-page":"256","article-title":"Deep evolutionary 3D diffusion heat maps for large-pose face alignment","author":"sun","year":"2018","journal-title":"Proc BMVC"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540094"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.410"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.446"},{"key":"ref53","article-title":"Rigid-motion scattering for image classification","author":"sifre","year":"2014"},{"key":"ref52","first-page":"4510","article-title":"Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation","author":"sandler","year":"2018","journal-title":"Proc CVPR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00103"},{"key":"ref10","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015","journal-title":"arXiv 1512 01274"},{"key":"ref54","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref17","first-page":"1","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"frankle","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref16","article-title":"Activation density driven energy-efficient pruning in training","author":"foldy-porto","year":"2020","journal-title":"arXiv 2002 02949"},{"key":"ref19","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc AISTATS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00215"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.218"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406585"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00941"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2781233"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080254"},{"key":"ref42","first-page":"1","article-title":"DARTS: Differentiable architecture search","author":"liu","year":"2019","journal-title":"Proc ICLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref44","first-page":"122","article-title":"ShuffleNet V2: Practical guidelines for efficient CNN architecture design","author":"ma","year":"2018","journal-title":"Proc ECCV"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.190"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0667-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0134-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.429"},{"key":"ref6","first-page":"1","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"2019","journal-title":"Proc ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01331-0"},{"key":"ref35","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref34","first-page":"7","author":"krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref37","first-page":"1","article-title":"Speeding-up convolutional neural networks using fine-tuned CP-decomposition","author":"lebedev","year":"2015","journal-title":"Proc ICLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00052"},{"key":"ref31","first-page":"74","article-title":"MixConv: Mixed depthwise convolutional kernels","author":"tan","year":"2019","journal-title":"Proc 30th Brit Mach Vis Conf (BMVC)"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.23"},{"key":"ref30","article-title":"Flattened convolutional neural networks for feedforward acceleration","author":"jin","year":"2014","journal-title":"arXiv 1412 5474"},{"key":"ref74","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"zhu","year":"2017","journal-title":"arXiv 1710 01878"},{"key":"ref33","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.241"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref2","first-page":"1","article-title":"OpenFace: An open source facial behavior analysis toolkit","author":"baltrusaitis","year":"2016","journal-title":"Proc IEEE Winter Conf Appl Comput Vis (WACV)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247980"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref38","article-title":"CTNet: Context-based tandem network for semantic segmentation","author":"li","year":"2021","journal-title":"arXiv 2104 09805"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_18"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.469"},{"key":"ref24","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.75"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00922"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00291"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.253"},{"key":"ref20","first-page":"1","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc NIPS"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9474031"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.453"},{"key":"ref22","first-page":"1","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"Proc NIPS"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2777489"},{"key":"ref28","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref27","first-page":"1","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","author":"iandola","year":"2017","journal-title":"Proc ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10208115\/09629225.pdf?arnumber=9629225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:55:49Z","timestamp":1692640549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9629225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":76,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3117685","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}