{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:49:05Z","timestamp":1778345345326,"version":"3.51.4"},"reference-count":102,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T00:00:00Z","timestamp":1673740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T00:00:00Z","timestamp":1673740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T00:00:00Z","timestamp":1673740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2020YFB1807601"],"award-info":[{"award-number":["2020YFB1807601"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20210324095209025"],"award-info":[{"award-number":["JCYJ20210324095209025"]}]},{"DOI":"10.13039\/501100011532","name":"Open Foundation of State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications","doi-asserted-by":"publisher","award":["SKLNST-2020-1-11"],"award-info":[{"award-number":["SKLNST-2020-1-11"]}],"id":[{"id":"10.13039\/501100011532","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2023,1,15]]},"DOI":"10.1109\/jiot.2022.3206388","type":"journal-article","created":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T19:38:13Z","timestamp":1663270693000},"page":"1066-1081","source":"Crossref","is-referenced-by-count":12,"title":["A Fine-Grained Attention Model for High Accuracy Operational Robot Guidance"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2457-8264","authenticated-orcid":false,"given":"Yinghao","family":"Chu","sequence":"first","affiliation":[{"name":"Department of Advanced Design and Systems Engineering, City University of Hong Kong, Kowloon Tong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0667-1150","authenticated-orcid":false,"given":"Daquan","family":"Feng","sequence":"additional","affiliation":[{"name":"Shenzhen Key Laboratory of Digital Creative Technology, the Guangdong Province Engineering Laboratory for Digital Creative Technology, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7816-502X","authenticated-orcid":false,"given":"Zuozhu","family":"Liu","sequence":"additional","affiliation":[{"name":"ZJU-UIUC Institute, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4767-3849","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"James Watt School of Engineering, University of Glasgow, Glasgow, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zizhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"AIATOR Company Ltd., Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5953-1824","authenticated-orcid":false,"given":"Zhenzhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Technical Management Center, China Media Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5322-222X","authenticated-orcid":false,"given":"Zhiyong","family":"Feng","sequence":"additional","affiliation":[{"name":"Key Laboratory of the Universal Wireless Communications, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5599-7683","authenticated-orcid":false,"given":"Xiang-Gen","family":"Xia","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Delaware, Newark, DE, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref57","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":"ref56","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":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.276"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref51","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2013","journal-title":"arXiv 1312 6229"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s40684-016-0039-x"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3005727"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2668395"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirp.2016.04.072"},{"key":"ref42","first-page":"430","article-title":"Machine learning for high-speed corner detection","author":"rosten","year":"2006","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref41","first-page":"404","article-title":"Surf: Speeded up robust features","author":"bay","year":"2006","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref43","first-page":"128","article-title":"Deep learning vs. traditional computer vision","author":"o\u2019mahony","year":"2019","journal-title":"Proc Sci Inf Conf"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252468"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2950048"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2017.1351644"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2016.03.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2016.11.016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s40684-016-0015-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2873426"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2017.1700030"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00314"},{"key":"ref101","author":"alpaydin","year":"2020","journal-title":"Introduction to Machine Learning"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CYBER.2014.6917527"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5772\/9668"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/9780470744055"},{"key":"ref36","first-page":"169","article-title":"Visual robot guidance from uncalibrated stereo","author":"cipolla","year":"1994","journal-title":"Real-time Computer Vision"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-017-1053-3"},{"key":"ref30","article-title":"On the stability of video detection and tracking","author":"zhang","year":"2016","journal-title":"arXiv 1611 06467"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.215"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459390"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.453"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2972000"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2820162"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3034925"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3107902"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2500960"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICGCIoT.2015.7380718"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3056466"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3079304"},{"key":"ref27","first-page":"137","article-title":"The control of a robot end-effector using photogrammetry","volume":"33","author":"clarke","year":"2000","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2694469"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2018.01.003"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/s16030335"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2014.2337336"},{"key":"ref97","first-page":"1","article-title":"Machine learning from imbalanced data sets 101","volume":"68","author":"provost","year":"2000","journal-title":"Proc AAAI Workshop Imbalanced Data Sets"},{"key":"ref96","first-page":"547","article-title":"Effectiveness of normalization pre-processing of big data to the machine learning performance","volume":"14","author":"jo","year":"2019","journal-title":"J Korean Inst Comm Sci"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2707140"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00990"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2018.01.006"},{"key":"ref98","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref17","author":"w\u00f6hler","year":"2012","journal-title":"3D Computer Vision - Efficient Methods and Applications"},{"key":"ref16","author":"sanz","year":"2012","journal-title":"Advances in Machine Vision"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1700202"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.sna.2014.07.014"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2002.806250"},{"key":"ref92","first-page":"122","article-title":"The OpenCV Library","volume":"120","author":"bradski","year":"2000","journal-title":"Dr Dobb’s J Softw Tools"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref91","first-page":"270","article-title":"A survey on deep transfer learning","author":"tan","year":"2018","journal-title":"Proc Int Joint Conf Artif Neural Netw"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref89","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"2014","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref86","first-page":"161","article-title":"The tradeoffs of large scale learning","author":"bottou","year":"2008","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref85","author":"redmon","year":"2016","journal-title":"Darknet Open source neural networks in c"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref87","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.pecs.2013.06.002"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAMET.2017.8253139"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref83","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc Int Conf Artif Intell Stat (ICAIS)"},{"key":"ref80","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.685"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2928603"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2019.01.012"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106622"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2996784"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2995162"},{"key":"ref71","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"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-003-0105-4"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref72","first-page":"2553","article-title":"Deep neural networks for object detection","author":"szegedy","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref68","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1038\/35058500"},{"key":"ref64","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref63","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref66","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref60","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref62","article-title":"DSSD: Deconvolutional single shot detector","author":"fu","year":"2017","journal-title":"arXiv 1701 06659"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10007705\/09893371.pdf?arnumber=9893371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T19:46:14Z","timestamp":1675107974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,15]]},"references-count":102,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2022.3206388","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,15]]}}}