{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T17:06:40Z","timestamp":1783184800794,"version":"3.54.6"},"reference-count":233,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100006319","name":"Centre National pour la Recherche Scientifique et Technique","doi-asserted-by":"publisher","award":["5UIZ2019"],"award-info":[{"award-number":["5UIZ2019"]}],"id":[{"id":"10.13039\/501100006319","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3266093","type":"journal-article","created":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T19:24:31Z","timestamp":1681154671000},"page":"35479-35516","source":"Crossref","is-referenced-by-count":287,"title":["Object Detection Using Deep Learning, CNNs and Vision Transformers: A Review"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0903-2602","authenticated-orcid":false,"given":"Ayoub Benali","family":"Amjoud","sequence":"first","affiliation":[{"name":"Image et Reconnaissance de Forme-Systèmes Intelligents et Communicants (IRF-SIC) Laboratory, Faculty of Sciences, Ibn Zohr University, Agadir, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4237-8576","authenticated-orcid":false,"given":"Mustapha","family":"Amrouch","sequence":"additional","affiliation":[{"name":"Image et Reconnaissance de Forme-Systèmes Intelligents et Communicants (IRF-SIC) Laboratory, Faculty of Sciences, Ibn Zohr University, Agadir, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2009.167"},{"key":"ref3","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Advances in Neural Information Processing Systems","volume":"25","author":"Krizhevsky"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.312"},{"key":"ref5","article-title":"Multi-view 3D object detection network for autonomous driving","author":"Chen","year":"2016","journal-title":"arXiv:1611.07759"},{"key":"ref6","article-title":"Detecting unexpected obstacles for self-driving cars: Fusing deep learning and geometric modeling","author":"Ramos","year":"2016","journal-title":"arXiv:1612.06573"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tim.2022.3146923"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883062"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3292522.3326028"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.425"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109071"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25446-8_4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3183112"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40763-5_50"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102276"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2021.102229"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.2992749"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2018.2794262"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3225455"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3068477"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2017.8029130"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.351"},{"key":"ref24","article-title":"Recent advances in object detection in the age of deep convolutional neural networks","author":"Agarwal","year":"2018","journal-title":"arXiv:1809.03193"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2018.2876865"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0149-9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2023.3238524"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01247-4"},{"key":"ref29","article-title":"A survey of self-supervised and few-shot object detection","author":"Huang","year":"2021","journal-title":"arXiv:2110.14711"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3051099"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104471"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.085"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/3189691"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114602"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2939201"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2001.990517"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2005.177"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2008.4587597"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/nn870"},{"issue":"1","key":"ref40","first-page":"1","article-title":"Visual categorization with bags of keypoints","volume-title":"Proc. Workshop Stat. Learn. Comput. Vis. ECCV","volume":"1","author":"Csurka"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.16"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2005.77"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47979-1_8"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000011202.85607.00"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2011.6126456"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/icip.2002.1038171"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_56"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/bf00994018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tit.1967.1053964"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref54","volume-title":"ImageNet Large Scale Visual Recognition Competition 2010 (ILSVRC2010)","year":"2019"},{"key":"ref55","volume-title":"MNIST Demos on Yann LeCun\u2019s Website","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1405.0312"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-51935-3_30"},{"key":"ref58","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref60","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019","journal-title":"arXiv:1905.11946"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01161"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw50498.2020.00203"},{"key":"ref63","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2016","journal-title":"arXiv:1612.03144"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00720"},{"key":"ref65","article-title":"Learning spatial fusion for single-shot object detection","author":"Liu","year":"2019","journal-title":"arXiv:1911.09516"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00913"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01079"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01146"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.91"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01204-1"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00972"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00975"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2858826"},{"key":"ref80","article-title":"YOLO9000: Better, faster, stronger","author":"Redmon","year":"2016","journal-title":"arXiv:1612.08242"},{"key":"ref81","first-page":"318","article-title":"MetaAnchor: Learning to detect objects with customized anchors","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00308"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1504.08083"},{"key":"ref85","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2013","journal-title":"arXiv:1311.2524"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00644"},{"key":"ref88","article-title":"ME R-CNN: Multi-expert R-CNN for object detection","author":"Lee","year":"2017","journal-title":"arXiv:1704.01069"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00615"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00377"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00984"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.98"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00300"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.260"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.324"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00836"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00091"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2006.68"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref100","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Dai"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00294"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00442"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.212"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00237"},{"key":"ref105","article-title":"DSSD: Deconvolutional single shot detector","author":"Fu","year":"2017","journal-title":"arXiv:1701.06659"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.557"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00062"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00609"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00206"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00963"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00671"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00526"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_15"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2009.5206848"},{"key":"ref116","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00647"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_22"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298594"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00094"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00093"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00978"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00037"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1137\/060659624"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108868"},{"key":"ref127","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2022.3148820"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/icds53782.2021.9626725"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref131","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00360"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00986"},{"key":"ref134","article-title":"Anchor DETR: Query design for transformer-based object detection","author":"Wang","year":"2021","journal-title":"arXiv:2109.07107"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00916"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2015.2437384"},{"key":"ref137","article-title":"Object detection networks on convolutional feature maps","author":"Ren","year":"2015","journal-title":"arXiv:1504.06066"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.89"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00730"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.314"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.92"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.135"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.76"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/wacv.2018.00125"},{"key":"ref145","article-title":"FSSD: Feature fusion single shot multibox detector","author":"Li","year":"2017","journal-title":"arXiv:1712.00960"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.447"},{"key":"ref147","article-title":"Residual features and unified prediction network for single stage detection","author":"Lee","year":"2017","journal-title":"arXiv:1707.05031"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1117\/12.2503001"},{"key":"ref149","article-title":"Weaving multi-scale context for single shot detector","author":"Chen","year":"2017","journal-title":"arXiv:1712.03149"},{"key":"ref150","article-title":"Single-shot bidirectional pyramid networks for high-quality object detection","author":"Wu","year":"2018","journal-title":"arXiv:1803.08208"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00751"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2018.2875449"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00980"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.444"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00757"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2018.2865280"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_28"},{"key":"ref158","first-page":"9333","article-title":"SNIPER: Efficient multi-scale training","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Singh"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/wacv.2018.00198"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00136"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00925"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_34"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.440"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.15"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.54"},{"key":"ref167","article-title":"RDSNet: A new deep architecture for reciprocal object detection and instance segmentation","author":"Wang","year":"2019","journal-title":"arXiv:1912.05070"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00215"},{"key":"ref169","article-title":"Beyond skip connections: Top-down modulation for object detection","author":"Shrivastava","year":"2016","journal-title":"arXiv:1612.06851"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00378"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_49"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_24"},{"key":"ref174","article-title":"Consistent optimization for single-shot object detection","author":"Kong","year":"2019","journal-title":"arXiv:1901.06563"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_21"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01392"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.593"},{"key":"ref179","article-title":"Cascade RetinaNet: Maintaining consistency for single-stage object detection","author":"Zhang","year":"2019","journal-title":"arXiv:1907.06881"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_13"},{"key":"ref182","article-title":"Light-head R-CNN: In defense of two-stage object detector","author":"Li","year":"2017","journal-title":"arXiv:1711.07264"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"ref184","first-page":"14335","article-title":"Efficient neural architecture transformation search in channel-level for object detection","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Peng"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00719"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_5"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2020.3002345"},{"key":"ref188","article-title":"RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free","author":"Fu","year":"2019","journal-title":"arXiv:1901.03353"},{"key":"ref189","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3050494"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01158"},{"key":"ref192","article-title":"CornerNet-lite: Efficient keypoint based object detection","author":"Law","year":"2019","journal-title":"arXiv:1904.08900"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_24"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01022"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01060"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00359"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00667"},{"key":"ref198","article-title":"PP-YOLO: An effective and efficient implementation of object detector","author":"Long","year":"2020","journal-title":"arXiv:2007.12099"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01283"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6958"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_6"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01053"},{"key":"ref204","article-title":"AutoAssign: Differentiable label assignment for dense object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2007.03496"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00511"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_32"},{"key":"ref208","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref209","article-title":"You only learn one representation: Unified network for multiple tasks","author":"Wang","year":"2021","journal-title":"arXiv:2105.04206"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00729"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01170"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2020.2980876"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3224815"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.3390\/rs14040871"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2022.113326"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/tetci.2017.2772792"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1016\/j.wasman.2021.12.001"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103182"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref223","article-title":"Deformable ConvNets v2: More deformable, better results","author":"Zhu","year":"2018","journal-title":"arXiv:1811.11168"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.308"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01008"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2022.3216771"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01337"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.243"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00745"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01167"},{"key":"ref233","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"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10098596.pdf?arnumber=10098596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T23:38:39Z","timestamp":1709249919000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10098596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":233,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3266093","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}