{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T15:07:10Z","timestamp":1761664030565},"reference-count":11,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2020,3,1]]},"DOI":"10.1587\/transinf.2019edl8165","type":"journal-article","created":{"date-parts":[[2020,2,29]],"date-time":"2020-02-29T22:10:37Z","timestamp":1583014237000},"page":"706-710","source":"Crossref","is-referenced-by-count":2,"title":["Fast Inference of Binarized Convolutional Neural Networks Exploiting Max Pooling with Modified Block Structure"],"prefix":"10.1587","volume":"E103.D","author":[{"given":"Ji-Hoon","family":"SHIN","sequence":"first","affiliation":[{"name":"School of Electronics & Information Engineering, Korea Aerospace University"}]},{"given":"Tae-Hwan","family":"KIM","sequence":"additional","affiliation":[{"name":"School of Electronics & Information Engineering, Korea Aerospace University"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] M. Rastegari, V. Ordonez, J. Redmon, and A. Farhadi, \u201cXNOR-Net: ImageNet classification using binary convolutional neural networks,\u201d Proc. European Conf. Computer Vision, pp.525-542, Springer, March 2016. 10.1007\/978-3-319-46493-0_32","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"2","unstructured":"[2] A. Krizhevsky and G. Hinton, \u201cLearning multiple layers of features from tiny images,\u201d Tech. Rep., Citeseer, 2009."},{"key":"3","unstructured":"[3] Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A.Y. Ng, \u201cReading digits in natural images with unsupervised feature learning,\u201d Proc. NIPS Workshop on Deep Learning and Unsupervised Feature Learning, pp.1-9, NeurIPS Foundation, Dec. 2011."},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] V. Sze, Y.-H. Chen, T.-J. Yang, and J.S. Emer, \u201cEfficient processing of deep neural networks: A tutorial and survey,\u201d Proc. IEEE, vol.105, no.12, pp.2295-2329, Dec. 2017. 10.1109\/jproc.2017.2761740","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"5","unstructured":"[5] M. Courbariaux and Y. Bengio, \u201cBinaryNet: training deep neural networks with weights and activations constrained to +1 or -1,\u201d arXiv: 1602.02830, 2017."},{"key":"6","unstructured":"[6] S. Zhou, Y. Wu, Z. Ni, X. Zhou, H. Wen, and Y. Zou, \u201cDoReFa-net: Training low bitwidth convolu-tional neural networks with low bitwidth gradients,\u201d arXiv preprint arXiv:1606.06160, 2016."},{"key":"7","unstructured":"[7] X. Lin, C. Zhao, and W. Pan, \u201cTowards accurate binary convolutional neural network,\u201d Proc. Advances in Neural Information Processing Systems, pp.345-353, Dec. 2017."},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] Y. Umuroglu, N.J. Fraser, G. Gambardella, M. Blott, P. Leong, M. Jahre, and K. Vissers, \u201cFINN: A framework for fast, scalable binarized neural network inference,\u201d Proc. International Symp. Field-Programmable Gate Arrays, pp.65-74, ACM, 2017. 10.1145\/3020078.3021744","DOI":"10.1145\/3020078.3021744"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] R. Andri, L. Cavigelli, D. Rossi, and L. Benini, \u201cYodaNN: An architecture for ultralow power binary-weight cnn acceleration,\u201d IEEE Trans. Comput.-Aided Design Integr. Circuits Syst., vol.37, no.1, pp.48-60, Jan. 2017. 10.1109\/tcad.2017.2682138","DOI":"10.1109\/TCAD.2017.2682138"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] Y. Wang, J. Lin, and Z. Wang, \u201cAn energy-efficient architecture for binary weight convolutional neural networks,\u201d IEEE Trans. VLSI Syst., vol.26, no.2, pp.280-293, Feb. 2018. 10.1109\/tvlsi.2017.2767624","DOI":"10.1109\/TVLSI.2017.2767624"},{"key":"11","unstructured":"[11] \u201cTensorFlow Lite,\u201d 2018. Software available from tensorflow.org."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/3\/E103.D_2019EDL8165\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,3,7]],"date-time":"2020-03-07T03:26:26Z","timestamp":1583551586000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/3\/E103.D_2019EDL8165\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,1]]},"references-count":11,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2019edl8165","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,1]]}}}