{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T18:20:22Z","timestamp":1778005222058,"version":"3.51.4"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61822101"],"award-info":[{"award-number":["61822101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061130221"],"award-info":[{"award-number":["62061130221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005089","name":"Beijing Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["L191001"],"award-info":[{"award-number":["L191001"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005089","name":"Beijing Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["4181002"],"award-info":[{"award-number":["4181002"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002358","name":"Zhuoyue Program of Beihang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002358","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2020M680299"],"award-info":[{"award-number":["2020M680299"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1109\/tits.2020.3041278","type":"journal-article","created":{"date-parts":[[2020,12,17]],"date-time":"2020-12-17T20:48:15Z","timestamp":1608238095000},"page":"4099-4110","source":"Crossref","is-referenced-by-count":61,"title":["SA-YOLOv3: An Efficient and Accurate Object Detector Using Self-Attention Mechanism for Autonomous Driving"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7796-5650","authenticated-orcid":false,"given":"Daxin","family":"Tian","sequence":"first","affiliation":[{"name":"Beijing Advanced Innovation Center for Big Data and Brain Computing, Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control, School of Transportation Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunmian","family":"Lin","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Big Data and Brain Computing, Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control, School of Transportation Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5331-6162","authenticated-orcid":false,"given":"Jianshan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Big Data and Brain Computing, Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control, School of Transportation Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5931-8310","authenticated-orcid":false,"given":"Xuting","family":"Duan","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Big Data and Brain Computing, Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control, School of Transportation Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2098-7637","authenticated-orcid":false,"given":"Yue","family":"Cao","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Big Data and Brain Computing, Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control, School of Transportation Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9848-372X","authenticated-orcid":false,"given":"Dezong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Aeronautical and Automotive Engineering, Loughborough University, Loughborough, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongpu","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref38","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref33","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref32","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref31","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref30","article-title":"CFENet: An accurate and efficient single-shot object detection for autonomous driving","author":"zhao","year":"2018","journal-title":"arXiv 1806 09790"},{"key":"ref37","first-page":"7354","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref36","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref35","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":"ref34","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00062"},{"key":"ref27","first-page":"4203","article-title":"Single-shot refinement neural network for object detecton","author":"zhang","year":"2018","journal-title":"Proc CVPR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.09.002"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.60"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2838132"},{"key":"ref22","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":"ref21","first-page":"354","article-title":"A unified multi-scale deep convolutional neural network for fast object detection","author":"cai","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref24","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.212"},{"key":"ref25","article-title":"FSSD: Feature fusion single shot multibox detector","author":"li","year":"2018","journal-title":"arXiv 1712 00960"},{"key":"ref50","article-title":"Bag of freebies for training object detection neural networks","author":"zhang","year":"2019","journal-title":"arXiv 1902 04103"},{"key":"ref51","first-page":"1","article-title":"Mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc ICLR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00059"},{"key":"ref10","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"arXiv 1511 07122"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref13","article-title":"BDD100K: A diverse driving dataset for heterogeneous multitask learning","author":"yu","year":"2018","journal-title":"arXiv 1805 04687"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.877062"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.117"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.465"},{"key":"ref18","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"li","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref5","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 (NIPS)"},{"key":"ref8","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref49","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"arXiv 1608 03983"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref46","year":"2018","journal-title":"Redmond"},{"key":"ref45","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"arXiv 1605 08695"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2922181"},{"key":"ref47","article-title":"Rethinking ImageNet pre-training","author":"he","year":"2018","journal-title":"arXiv 1811 08883"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-75988-8_28"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102827"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/78.157290"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9766829\/09298480.pdf?arnumber=9298480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T21:51:52Z","timestamp":1653947512000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9298480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5]]},"references-count":52,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tits.2020.3041278","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5]]}}}