{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T11:47:08Z","timestamp":1780573628347,"version":"3.54.1"},"reference-count":68,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["62001003"],"award-info":[{"award-number":["62001003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2008085QF284"],"award-info":[{"award-number":["2008085QF284"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2020M671851"],"award-info":[{"award-number":["2020M671851"]}],"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]]},"DOI":"10.1109\/tits.2022.3219676","type":"journal-article","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T20:31:54Z","timestamp":1668112314000},"page":"1-15","source":"Crossref","is-referenced-by-count":29,"title":["FPT: Fine-Grained Detection of Driver Distraction Based on the Feature Pyramid Vision Transformer"],"prefix":"10.1109","author":[{"given":"HaiTao","family":"Wang","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, School of Electronics and Information Engineering, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9605-4331","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, School of Electronics and Information Engineering, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8023-9075","authenticated-orcid":false,"given":"ZhiXiang","family":"Huang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, School of Electronics and Information Engineering, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, School of Electronics and Information Engineering, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JianMing","family":"Lv","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, School of Electronics and Information Engineering, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JingMin","family":"Xi","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, School of Electronics and Information Engineering, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"BoCai","family":"Wu","sequence":"additional","affiliation":[{"name":"38th Research Institute of China Electronics Technology Group Corporation, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1321-6022","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, Chinese Academy of Sciences, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ZhongCheng","family":"Wu","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, Chinese Academy of Sciences, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Global Status Report on Road Safety","year":"2018"},{"key":"ref2","volume-title":"Global Status Report on Road Safety 2015","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2013.6008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2261988"},{"key":"ref5","article-title":"Real-time distracted driver posture classification","volume-title":"arXiv:1706.09498","author":"Abouelnaga","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3055545"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.104"},{"key":"ref8","volume-title":"System and method for responding to driver behavior","author":"Fung","year":"2012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2917866"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2016.04.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2247760"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2496157"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2015.217"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00150"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISPCE-ASIA53453.2021.9652435"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.2995555"},{"key":"ref17","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"arXiv:2010.11929","author":"Dosovitskiy","year":"2020"},{"key":"ref18","article-title":"Transformer in transformer","volume-title":"arXiv:2103.00112","author":"Han","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref22","article-title":"Lawin transformer: Improving semantic segmentation transformer with multi-scale representations via large window attention","volume-title":"arXiv:2201.01615","author":"Yan","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524258"},{"key":"ref24","article-title":"Very deep transformers for neural machine translation","volume-title":"arXiv:2008.07772","author":"Liu","year":"2020"},{"key":"ref25","article-title":"All SMILES variational autoencoder","author":"Alperstein","year":"2019","journal-title":"arXiv:1905.13343"},{"key":"ref26","first-page":"411","article-title":"A pattern recognition system for detecting use of mobile phones while driving","volume-title":"Proc. Int. Conf. Comput. Vis. Theory Appl. (VISAPP)","volume":"2","author":"Berri"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2475721"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICVES.2011.5983823"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2011.0116"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.13"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301397"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-019-01589-z"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SSIAI.2018.8470309"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2018.5172"},{"key":"ref35","volume-title":"State Farm Distracted Driver Detection","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29859-3_23"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-021-05949-1"},{"key":"ref38","article-title":"Attention is all you need","volume-title":"arXiv:1706.03762","author":"Vaswani","year":"2017"},{"key":"ref39","article-title":"Language models are few-shot learners","volume-title":"arXiv:2005.14165","author":"Brown","year":"2020"},{"key":"ref40","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv:1810.04805","author":"Devlin","year":"2018"},{"key":"ref41","article-title":"DeepViT: Towards deeper vision transformer","volume-title":"arXiv:2103.11886","author":"Zhou","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref43","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref47","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"arXiv:2104.13840","author":"Chu","year":"2021"},{"key":"ref48","first-page":"103","article-title":"Benchmarking deep learning models for driver distraction detection","volume-title":"Proc. Benchmarking","author":"Mase"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref50","article-title":"Do we really need explicit position encodings for vision transformers?","volume-title":"arXiv:2102.10882","author":"Chu","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/4125865"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.42"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2015.473"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2014.6856610"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2012.09.018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2020.115960"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref66","article-title":"MiniLM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume-title":"arXiv:2002.10957","author":"Wang","year":"2020"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref68","article-title":"Lite transformer with long-short range attention","volume-title":"arXiv:2004.11886","author":"Wu","year":"2020"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/4358928\/09945665.pdf?arnumber=9945665","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:23:52Z","timestamp":1706757832000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9945665\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tits.2022.3219676","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}