{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:58Z","timestamp":1740169258672,"version":"3.37.3"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP) Grant"},{"DOI":"10.13039\/501100014188","name":"Korea Government Ministry of Science and ICT","doi-asserted-by":"publisher","award":["2022-0-00759"],"award-info":[{"award-number":["2022-0-00759"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP) grant"},{"DOI":"10.13039\/501100014188","name":"Korea Government Ministry of Science and ICT (MSIT) Artificial Intelligence Innovation Hub","doi-asserted-by":"publisher","award":["2021-0-02068"],"award-info":[{"award-number":["2021-0-02068"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3197219","type":"journal-article","created":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T19:50:29Z","timestamp":1659988229000},"page":"88251-88262","source":"Crossref","is-referenced-by-count":1,"title":["A New Pointwise Convolution in Deep Neural Networks Through Extremely Fast and Non Parametric Transforms"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0028-8660","authenticated-orcid":false,"given":"Joonhyun","family":"Jeong","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5641-5596","authenticated-orcid":false,"given":"Incheon","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7440-5532","authenticated-orcid":false,"given":"Eunseop","family":"Shin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2677-3186","authenticated-orcid":false,"given":"Sung-Ho","family":"Bae","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref12","article-title":"An analysis of deep neural network models for practical applications","volume-title":"arXiv:1605.07678","author":"Canziani","year":"2016"},{"key":"ref13","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","volume-title":"arXiv:1704.04861","author":"Andrew Howard","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00474"},{"key":"ref15","article-title":"ShuffleNet: An extremely efficient convolutional neural network for mobile devices","volume-title":"arXiv:1707.01083","author":"Zhang","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01204"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2021.1953719"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1117\/1.JRS.11.042616"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1117\/12.2281707"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77383-4_7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2018.2866684"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3616-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCC.2008.4625662"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1142\/S1793536911000787"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2009.11.001"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1965-0178586-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900182"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.03.058"},{"key":"ref30","first-page":"194","article-title":"Walsh\u2013Hadamard transform for facial feature extraction in face recognition","volume":"29","author":"Hassan","year":"2007","journal-title":"World Acad. Sci., Eng. Technol."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2362652"},{"key":"ref32","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","volume-title":"arXiv:1602.07360","author":"Iandola","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.200"},{"key":"ref34","article-title":"Constructing fast network through deconstruction of convolution","volume-title":"arXiv:1806.07370","author":"Jeon","year":"2018"},{"article-title":"Improving the speed of neural networks on CPUs","volume-title":"Proc. Deep Learn. Unsupervised Feature Learn. Workshop","author":"Vanhoucke","key":"ref35"},{"key":"ref36","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta"},{"key":"ref37","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref38","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"arXiv:1510.00149","author":"Han","year":"2015"},{"key":"ref39","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","volume-title":"arXiv:1511.00363","author":"Courbariaux","year":"2015"},{"key":"ref40","article-title":"BinaryNet: Training deep neural networks with weights and activations constrained to +1 or \u22121","volume-title":"arXiv:1602.02830","author":"Courbariaux","year":"2016"},{"key":"ref41","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume-title":"arXiv:1609.07061","author":"Hubara","year":"2016"},{"key":"ref42","article-title":"Local binary convolutional neural networks","volume-title":"arXiv:1608.06049","author":"Juefei-Xu","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2329460"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CISP.2013.6743947"},{"issue":"1","key":"ref45","first-page":"81","article-title":"Image compression using the discrete cosine transform","volume":"4","author":"Watson","year":"1994","journal-title":"Math. J."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-61316-1_2"},{"volume-title":"Discrete Cosine Transform: Algorithms, Advantages, Applications","year":"2014","author":"Rao","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1969.6869"},{"key":"ref49","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"arXiv:1502.03167","author":"Ioffe","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/78.558495"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref53","article-title":"Opening the black box of deep neural networks via information","volume-title":"arXiv:1703.00810","author":"Shwartz-Ziv","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref55","first-page":"4261","article-title":"Can we gain more from orthogonality regularizations in training deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bansal"},{"key":"ref56","article-title":"Regularizing CNNs with locally constrained decorrelations","volume-title":"arXiv:1611.01967","author":"Rodr\u00edguez","year":"2016"},{"key":"ref57","article-title":"All you need is a good init","volume-title":"arXiv:1511.06422","author":"Mishkin","year":"2015"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11768"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.539"},{"key":"ref60","article-title":"Rethinking channel dimensions for efficient model design","volume-title":"arXiv:2007.00992","author":"Han","year":"2020"},{"key":"ref61","article-title":"Breaking the softmax bottleneck: A high-rank RNN language model","volume-title":"arXiv:1711.03953","author":"Yang","year":"2017"},{"key":"ref62","first-page":"374","article-title":"A spline theory of deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Balestriero"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2020.3042100"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.30"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref66","article-title":"FDDB: A benchmark for face detection in unconstrained settings","volume":"2","author":"Jain","year":"2010"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09852205.pdf?arnumber=9852205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T02:02:10Z","timestamp":1710381730000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9852205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3197219","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2022]]}}}