{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T12:19:44Z","timestamp":1775218784623,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61472450"],"award-info":[{"award-number":["61472450"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of\u00a0Hunan Province","doi-asserted-by":"publisher","award":["2017JJ3417"],"award-info":[{"award-number":["2017JJ3417"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Plan of Hunan","award":["2016TP1003"],"award-info":[{"award-number":["2016TP1003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2873315","type":"journal-article","created":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T18:35:28Z","timestamp":1538418928000},"page":"56750-56764","source":"Crossref","is-referenced-by-count":41,"title":["DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity Recognition"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6336-0228","authenticated-orcid":false,"given":"Zhan","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osolo Ian","family":"Raymond","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"zhou","year":"2017","journal-title":"Incremental network quantization Towards lossless cnns with low-precision weights"},{"key":"ref38","author":"hubara","year":"2016","journal-title":"Quantized neural networks Training neural networks with low precision weights and activations"},{"key":"ref33","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2833888"},{"key":"ref37","author":"zhou","year":"2016","journal-title":"DoReFa-Net Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients"},{"key":"ref36","author":"li","year":"2016","journal-title":"Ternary Weight Networks"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1049\/el:19901121"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref28","first-page":"46","article-title":"Deep convolutional neural networks for human activity recognition with smartphone sensors","author":"ronao","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3134230.3134231"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2777003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref1","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref20","author":"cook","year":"2015","journal-title":"Activity Learning Discovering Recognizing and Predicting Human Behavior from Sensor Data"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"115","DOI":"10.3390\/s16010115","article-title":"Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition","volume":"16","author":"ord\u00f3\u00f1ez","year":"2016","journal-title":"SENSORS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2493988.2494349"},{"key":"ref24","author":"alsheikh","year":"2015","journal-title":"Deep activity recognition models with triaxial accelerometer"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"706","DOI":"10.5220\/0005828407060713","article-title":"Motion classification for analyzing the order picking process using mobile sensors","author":"feldhorst","year":"2016","journal-title":"Proc Int Conf Pattern Recognit Appl Methods"},{"key":"ref26","first-page":"454","article-title":"Deep, convolutional, and recurrent models for human activity recognition using wearables","volume":"61","author":"hammerla","year":"2016","journal-title":"J Sci Comput"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCI-CC.2015.7259385"},{"key":"ref50","author":"ioffe","year":"2015","journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2012.12.014"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref54","author":"zeiler","year":"2012","journal-title":"ADADELTA An Adaptive Learning Rate Method"},{"key":"ref53","author":"micucci","year":"2016","journal-title":"UniMiB SHAR A new dataset for human activity recognition using acceleration data from smartphones"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2012.13"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref40","first-page":"1508","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref12","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref13","author":"esser","year":"2016","journal-title":"Convolutional Networks for Fast Energy-Efficient Neuromorphic Computing"},{"key":"ref14","author":"han","year":"2015","journal-title":"Deep compression Compressing deep neural networks with pruning trained quantization and huffman coding"},{"key":"ref15","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 (NIPS)"},{"key":"ref16","author":"courbariaux","year":"2016","journal-title":"Binarized neural networks Training deep neural networks with weights and activations constrained to +1 or ?1"},{"key":"ref17","author":"rastegari","year":"2016","journal-title":"Xnor-net Imagenet classification using binary convolutional neural networks"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2014.7082765"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3123021.3123046"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2608777"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2770178"},{"key":"ref6","first-page":"3995","article-title":"Deep convolutional neural networks on multichannel time series for human activity recognition","author":"yang","year":"2015","journal-title":"Proc Intern Joint Conf Artificial Intel (IJCAI)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2810264"},{"key":"ref8","first-page":"10","article-title":"Computing’s energy problem (and what we can do about it)","author":"horowitz","year":"2014","journal-title":"IEEE Int Solid-State Circuits Conf Dig Tech Papers"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2753830"},{"key":"ref49","author":"mu?a","year":"2016","journal-title":"Faster Population Counts using AVX2 Instructions"},{"key":"ref9","author":"szegedy","year":"2016","journal-title":"Inception-v4 inception-resnet and the impact of residual connections on learning"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_48"},{"key":"ref45","author":"rueda","year":"2018","journal-title":"Learning attribute representation for human activity recognition"},{"key":"ref48","first-page":"1737","article-title":"Deep learning with limited numerical precision","author":"gupta","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref47","first-page":"1707","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","author":"alistarh","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF02678430"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.430"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"679e","DOI":"10.3390\/s18020679","article-title":"Comparison of feature learning methods for human activity recognition using wearable sensors","volume":"18","author":"li","year":"2018","journal-title":"SENSORS"},{"key":"ref43","author":"bengio","year":"2013","journal-title":"Estimating or propagating gradients through stochastic neurons"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08478282.pdf?arnumber=8478282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T17:54:47Z","timestamp":1643219687000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8478282\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2873315","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}