{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:46:55Z","timestamp":1784270815114,"version":"3.55.0"},"reference-count":290,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100007162","name":"Commonwealth of Australia through the Defence Science and Technology Group, Department of Defence","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007162","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tits.2025.3530678","type":"journal-article","created":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T18:34:34Z","timestamp":1739558074000},"page":"2851-2879","source":"Crossref","is-referenced-by-count":49,"title":["A Guide to Image- and Video-Based Small Object Detection Using Deep Learning: Case Study of Maritime Surveillance"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9542-759X","authenticated-orcid":false,"given":"Aref","family":"Miri Rekavandi","sequence":"first","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1759-2941","authenticated-orcid":false,"given":"Lian","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7250-7407","authenticated-orcid":false,"given":"Farid","family":"Boussaid","sequence":"additional","affiliation":[{"name":"Department of Electrical, Electronic and Computer Engineering, The University of Western Australia, Perth, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4619-734X","authenticated-orcid":false,"given":"Abd-Krim","family":"Seghouane","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, The University of Melbourne, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen","family":"Hoefs","sequence":"additional","affiliation":[{"name":"Submarine Optronics Division, the Undersea Combat Systems Division, and the Undersea Command and Control Maritime Division, Defence Science and Technology Group, Perth, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6603-3257","authenticated-orcid":false,"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00533"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2018.8484698"},{"key":"ref5","first-page":"1","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. NeurIPS","volume":"32","author":"Herdade"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/s21041270"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09924-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296411"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3077139"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3472810"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108585"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00607-021-01038-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-06979-y"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/rs14020339"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00057"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-5348-3_9"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-5655-2_15"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09749-x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2009.10.002"},{"key":"ref21","article-title":"MaskGRU: Tracking small objects in the presence of large background motions","author":"Roros","year":"2022","journal-title":"arXiv:2201.00467"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-021-04409-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref26","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. NeurIPS","volume":"28","author":"Ren"},{"key":"ref27","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","volume-title":"Proc. NeurIPS","volume":"29","author":"Dai"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00975"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref35","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref37","volume-title":"YOLOv5","author":"Jocher","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.02325"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107149"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_33"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413634"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-04230-4"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2016.2515127"},{"key":"ref51","first-page":"9288","article-title":"Optimal visual search based on a model of target detectability in natural images","volume-title":"Proc. NeurIPS","volume":"33","author":"Rashidi"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICM.2017.8268815"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3390\/s18092995"},{"key":"ref54","volume-title":"International Shipping Facts and Figures\u2014Information Resources on Trade, Safety, Security, and the Environment","year":"2011"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18178\/joig.9.4.122-134"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2017.12.033"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2872166"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2634580"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.103910"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2020.09.022"},{"key":"ref61","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2021\/8793101","article-title":"Survey on deep learning-based marine object detection","volume":"2021","author":"Zhang","year":"2021","journal-title":"J. Adv. Transp."},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3005231"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104471"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290594"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3390\/jmse9040397"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref67","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref69","article-title":"GridMask data augmentation","author":"Chen","year":"2020","journal-title":"arXiv:2001.04086"},{"key":"ref70","article-title":"Data augmentation generative adversarial networks","author":"Antoniou","year":"2017","journal-title":"arXiv:1711.04340"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00760"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_34"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.5121\/csit.2019.91713"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00018"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093394"},{"key":"ref78","article-title":"Stitcher: Feedback-driven data provider for object detection","author":"Chen","year":"2020","journal-title":"arXiv:2004.12432"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2982166"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92307-5_45"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_13"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.211"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00982"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2916592"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00084"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00093"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_6"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2018.00024"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2019.01.012"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref91","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":"ref92","article-title":"Toward transformer-based object detection","author":"Beal","year":"2020","journal-title":"arXiv:2012.09958"},{"key":"ref93","first-page":"1","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","volume-title":"Proc. NeurIPS","volume":"34","author":"Fang"},{"key":"ref94","article-title":"ViDT: An efficient and effective fully transformer-based object detector","author":"Song","year":"2021","journal-title":"arXiv:2110.03921"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20397"},{"key":"ref97","article-title":"D2ETR: Decoder-only DETR with computationally efficient cross-scale attention","author":"Lin","year":"2022","journal-title":"arXiv:2203.00860"},{"key":"ref98","article-title":"Guiding query position and performing similar attention for transformer-based detection heads","author":"Jiang","year":"2021","journal-title":"arXiv:2108.09691"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref100","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103620"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref103","first-page":"1","article-title":"FP-DETR: Detection transformer advanced by fully pre-training","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07089-5"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3198490"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-021-01170-3"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108548"},{"key":"ref108","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.3390\/s21155103"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.3390\/s21217422"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_40"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.3390\/rs14020420"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2723-1"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01511-7"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2642789"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_5"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3004636"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC51459.2021.9415217"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00016"},{"key":"ref121","article-title":"Intrinsic relationship reasoning for small object detection","author":"Fu","year":"2020","journal-title":"arXiv:2009.00833"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.093"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103615"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi10030170"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.245"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20890-5_43"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref129","article-title":"A normalized Gaussian Wasserstein distance for tiny object detection","author":"Wang","year":"2021","journal-title":"arXiv:2110.13389"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3095305"},{"key":"ref131","article-title":"Seq-NMS for video object detection","author":"Han","year":"2016","journal-title":"arXiv:1602.08465"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.330"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_30"},{"key":"ref134","first-page":"5686","article-title":"Mobile video object detection with temporally-aware feature maps","volume-title":"Proc. CVPR","author":"Liu"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065720500343"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/s10694-019-00832-w"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.44"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.257"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475285"},{"key":"ref142","article-title":"TransVOD: End-to-end video object detection with spatial\u2013temporal transformers","author":"Zhou","year":"2022","journal-title":"arXiv:2201.05047"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107929"},{"key":"ref144","article-title":"Spatio-temporal tubelet feature aggregation and object linking in videos","author":"Cores","year":"2020","journal-title":"arXiv:2004.00451"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.3390\/rs11171965"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2021.109435"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.3390\/rs12203316"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.3390\/rs13030499"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssci.2020.104812"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/BigComp48618.2020.00-25"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2171\/1\/012033"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.3390\/s21113641"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.3390\/rs13071327"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.355"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1017\/S0373463321000783"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican1277-108"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564669"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1145\/3458380.3458387"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2000.855874"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564887"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2016.2637439"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2018.2833382"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.3390\/rs13010056"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1080\/2150704X.2021.1979271"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.3390\/s19163523"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-021-00831-6"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2848901"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/9440212"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2021.723336"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1908.08681"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.3390\/rs13040660"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2964540"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93046-2_50"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.3390\/rs13163059"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.3390\/sym13040623"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.3390\/rs13163192"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3053956"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2020.1811422"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.3390\/rs13234840"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01498"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01077"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2015.7301753"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.159"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2897980"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00121"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639077"},{"key":"ref189","article-title":"ENet: A deep neural network architecture for real-time semantic segmentation","author":"Paszke","year":"2016","journal-title":"arXiv:1606.02147"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3149297"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00195"},{"key":"ref194","first-page":"1","article-title":"Image-based ship detection and classification for unmanned surface vehicle using real-time object detection neural networks","volume-title":"Proc. ISOPE","author":"Lee"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC49870.2020.9289620"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2865686"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2775524"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2836399"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.12.284"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW46912.2020.9106019"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1029\/2019EA000960"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/ISSI47111.2019.9043694"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00374"},{"key":"ref205","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv:1904.07850"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.3390\/s18082702"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3113473"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00220"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3076050"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/SITIS.2018.00017"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.3390\/app8060936"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00049"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2907277"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/7194342"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.3390\/sym13020308"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639373"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759186"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21227-7_23"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.232"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6706807"},{"key":"ref223","article-title":"Challenging environments for traffic sign detection: Reliability assessment under inclement conditions","author":"Temel","year":"2019","journal-title":"arXiv:1902.06857"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54193-8_14"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00028"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545307"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428458"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1186\/s12544-019-0390-4"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2402438"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2014.00147"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2014.10.002"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117983"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3072311"},{"key":"ref240","article-title":"XView: Objects in context in overhead imagery","author":"Lam","year":"2018","journal-title":"arXiv:1802.07856"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.11.002"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.5220\/0006120603240331"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2015.7301727"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-19816-9_10"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2412251"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.157"},{"key":"ref248","article-title":"FGSD: A dataset for fine-grained ship detection in high resolution satellite images","author":"Chen","year":"2020","journal-title":"arXiv:2003.06832"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3104230"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/AIPR.2011.6176352"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06430-2_53"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0748-y"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298768"},{"key":"ref254","first-page":"7","article-title":"The DGPF test on digital aerial camera evaluation\u2014Overview and test design. photogrammetrie\u2013fernerkundung\u2013geoinformation 2, 73\u201382 (2010)","volume-title":"Proc. PFG","author":"Cramer"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2564408"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2954464"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00764-5_51"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913882"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3020556"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-020-01614-2"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3145467"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2923016"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00712"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.557"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00840"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00520"},{"key":"ref273","first-page":"1","article-title":"FreeAnchor: Learning to match anchors for visual object detection","volume-title":"Proc. NeurIPS","author":"Zhang"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00754"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414162"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00615"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3002345"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1177\/1729881420932715"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/1060182"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00311"},{"key":"ref283","article-title":"Leveraging synthetic data in object detection on unmanned aerial vehicles","author":"Kiefer","year":"2021","journal-title":"arXiv:2112.12252"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/34.868684"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2008.924285"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-009-0285-8"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299099"},{"issue":"4","key":"ref288","first-page":"415","article-title":"Image-based ship detection using deep learning","volume":"10","author":"Lee","year":"2020","journal-title":"Ocean Syst. Eng."},{"key":"ref289","article-title":"TaskCLIP: Extend large vision-language model for task oriented object detection","author":"Chen","year":"2024","journal-title":"arXiv:2403.08108"},{"key":"ref290","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2021","journal-title":"arXiv:2109.10852"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/10909032\/10887401.pdf?arnumber=10887401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T06:15:07Z","timestamp":1741068907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887401\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":290,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3530678","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}