{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T03:55:53Z","timestamp":1776138953908,"version":"3.50.1"},"reference-count":61,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2016YFB1200402"],"award-info":[{"award-number":["2016YFB1200402"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52172313"],"award-info":[{"award-number":["52172313"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hunan Provincial Key Research and Development Program","award":["2019SK2171"],"award-info":[{"award-number":["2019SK2171"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Instrum. Meas."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tim.2022.3219468","type":"journal-article","created":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T20:36:54Z","timestamp":1668544614000},"page":"1-14","source":"Crossref","is-referenced-by-count":55,"title":["YOLO-Former: Marrying YOLO and Transformer for Foreign Object Detection"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0408-5529","authenticated-orcid":false,"given":"Yuan","family":"Dai","sequence":"first","affiliation":[{"name":"School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1819-9153","authenticated-orcid":false,"given":"Weiming","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9196-7839","authenticated-orcid":false,"given":"Heng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Metro Group Company Ltd., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4756-1174","authenticated-orcid":false,"given":"Wei","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5968-1865","authenticated-orcid":false,"given":"Kejun","family":"Long","sequence":"additional","affiliation":[{"name":"Hunan Provincial Key Laboratory of Smart Roadway and Cooperative Vehicle-Infrastructure Systems, Changsha University of Science and Technology, Changsha, China"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref38","article-title":"Pyramid attention networks for image restoration","author":"mei","year":"2020","journal-title":"arXiv 2004 13824"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref32","first-page":"1","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref31","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref30","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref37","article-title":"Transformers meet visual learning understanding: A comprehensive review","author":"yang","year":"2022","journal-title":"arXiv 2203 12944"},{"key":"ref36","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2021","journal-title":"Proc 9th Int Conf Learn Represent (ICLR)"},{"key":"ref35","article-title":"Swin transformer V2: Scaling up capacity and resolution","author":"liu","year":"2021","journal-title":"arXiv 2111 09883"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"ref27","first-page":"1922","article-title":"FCOS: A simple and strong anchor-free object detector","volume":"44","author":"tian","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3151165"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3128961"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref21","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref26","first-page":"21","article-title":"SSD: Single shot MultiBox detector","volume":"9905","author":"liu","year":"2016","journal-title":"Proc 14th Eur Conf"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref50","article-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"wang","year":"2022","journal-title":"arXiv 2207 02696"},{"key":"ref51","article-title":"HorNet: Efficient high-order spatial interactions with recursive gated convolutions","author":"rao","year":"2022","journal-title":"arXiv 2207 14284"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref58","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref57","author":"kazaj","year":"2021","journal-title":"YOLOv5-GradCAM"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref53","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"ge","year":"2021","journal-title":"arXiv 2107 08430"},{"key":"ref52","article-title":"A ConvNet for the 2020 s","author":"liu","year":"2022","journal-title":"arXiv 2201 03545"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2343217"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3095305"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3486618"},{"key":"ref13","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc 9th Int Conf Learn Represent (ICLR)"},{"key":"ref14","first-page":"3","article-title":"CBAM: Convolutional block attention module","volume":"11211","author":"woo","year":"2018","journal-title":"Proc 15th Eur Conf"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-48318-9_3"},{"key":"ref16","author":"jocher","year":"2021","journal-title":"Ultralytics\/YOLOv5 V6 0—YOLOv5n ‘nano’ models roboflow integration TensorFlow export OpenCV DNN support"},{"key":"ref17","first-page":"1967","article-title":"Pelee: A real-time object detection system on mobile devices","author":"wang","year":"2018","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2022.3201400"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3136183"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2978912"},{"key":"ref5","first-page":"11","article-title":"DifferentNet: Neural network for foreign objects foreground detection in metro","volume":"49","author":"liu","year":"2021","journal-title":"J South China Univ Technol Natural Sci"},{"key":"ref8","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref7","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2642789"},{"key":"ref46","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref45","article-title":"Bridging nonlinearities and stochastic regularizers with Gaussian error linear units","author":"hendrycks","year":"2016","journal-title":"arXiv 1606 08415"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"ref41","author":"paddle","year":"2022","journal-title":"Awesome-deeplearning"},{"key":"ref44","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00314"}],"container-title":["IEEE Transactions on Instrumentation and Measurement"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/19\/9717300\/09953039.pdf?arnumber=9953039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:13:43Z","timestamp":1670872423000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9953039\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tim.2022.3219468","relation":{},"ISSN":["0018-9456","1557-9662"],"issn-type":[{"value":"0018-9456","type":"print"},{"value":"1557-9662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}