{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:41:02Z","timestamp":1783438862083,"version":"3.54.6"},"reference-count":183,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Scientific Technological Innovation Research Project of the Ministry of Education"},{"DOI":"10.13039\/501100001809","name":"Joint Funds of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}],"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":["62076192"],"award-info":[{"award-number":["62076192"]}],"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":["61902298"],"award-info":[{"award-number":["61902298"]}],"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":["61573267"],"award-info":[{"award-number":["61573267"]}],"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":["61906150"],"award-info":[{"award-number":["61906150"]}],"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":["62276199"],"award-info":[{"award-number":["62276199"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Cheung Kong Scholars and Innovative Research Team in University","award":["IRT 15R53"],"award-info":[{"award-number":["IRT 15R53"]}]},{"name":"Science and Technology Innovation Project from the Chinese Ministry of Education"},{"name":"China Postdoctoral Fund","award":["2022T150506"],"award-info":[{"award-number":["2022T150506"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3389454","type":"journal-article","created":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T15:18:44Z","timestamp":1713885524000},"page":"5900-5920","source":"Crossref","is-referenced-by-count":61,"title":["Multiscale Deep Learning for Detection and Recognition: A Comprehensive Survey"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0115-8008","authenticated-orcid":false,"given":"Mengjiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7372-9180","authenticated-orcid":false,"given":"Zhixi","family":"Feng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4796-5737","authenticated-orcid":false,"given":"Shuyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biao","family":"Hou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Jiao","year":"2017","journal-title":"Deep Learning, Optimization and Recognition"},{"key":"ref2","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. NeurIPS","volume":"25","author":"Krizhevsky"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3229161"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref9","author":"Squire","year":"2012","journal-title":"Fundamental Neuroscience"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511801556"},{"key":"ref11","volume-title":"Neuroscience: Exploring the Brain","author":"Bear","year":"2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/757582976"},{"key":"ref13","volume-title":"Principles of Neural Science","volume":"4","author":"Kandel","year":"2000"},{"key":"ref14","volume-title":"Neuroscience","author":"Purves","year":"2018"},{"key":"ref15","author":"Wang","year":"2010","journal-title":"Image Local Invariant Features and Descriptors"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00336961"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1971.223290"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0146-664X(76)80012-3"},{"key":"ref19","article-title":"A representation for visual information","author":"Crowley","year":"1982"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1983.1095851"},{"issue":"6","key":"ref21","first-page":"33","article-title":"Pyramid methods in image processing","volume":"29","author":"Adelson","year":"1984","journal-title":"RCA Eng."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-03174-2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1995.537667"},{"key":"ref24","first-page":"3","article-title":"Basic theory of pattern observation","volume-title":"Technical Group on Automata and Automatic Control","author":"Iijima"},{"key":"ref25","first-page":"1019","article-title":"Scale-space filtering","volume-title":"Proc. IJCAI","author":"Witkin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767749"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/34.49051"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0262-8856(92)90024-W"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-6465-9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008045108935"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44935-3_11"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1989-1008470-5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/34.192463"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1190\/1.1441328"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1190\/1.1441329"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/0515056"},{"key":"ref38","first-page":"1985","article-title":"Principe d\u2019incertitude, bases hilbertiennes et algebres d\u2019operateurs","volume":"662","author":"Meyer","year":"1985","journal-title":"S\u00e9minaire Bourbaki"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1063\/1.527388"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF01205550"},{"key":"ref41","first-page":"227","article-title":"Une nouvelle base d\u2019ondelettes de L 2 (Rn)","volume":"67","author":"Lemari\u00e9","year":"1988","journal-title":"J. Math. Pures Appl."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1063\/1.4823126"},{"key":"ref43","first-page":"91","article-title":"Advances and prespective in wavelet theory and its application","volume":"21","author":"Jiao","year":"1993","journal-title":"Acta Electronica Sinica"},{"key":"ref44","first-page":"177","article-title":"Advances and perspective on image perception and recognition in multiscale transform domains","volume":"29","author":"Jiao","year":"2006","journal-title":"Chin. J. Comput."},{"key":"ref45","volume-title":"Image Multiscale Geometric Analysis: Theory and Applications\u2014Beyond Wavelets","author":"Jiao","year":"2008"},{"key":"ref46","first-page":"1975","article-title":"Development and prospect of image multiscale geometric analysis","volume":"31","author":"Jiao","year":"2003","journal-title":"Acta Electronica Sinica"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1006\/acha.1997.0208"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1065705119"},{"key":"ref49","first-page":"105","article-title":"Curvelets\u2014A surprisingly effective nonadaptive representation for objects with edges","volume-title":"Curve and Surface Fitting","author":"Cand\u00e8s","year":"1999"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1018031261"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2000.901045"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-56205-1_3"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2002.1038034"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1117\/12.613494"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.877076"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.11897\/SP.J.1016.2016.00835"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3170001"},{"key":"ref58","volume-title":"Theory of Neural Networks","author":"Jiao","year":"1990"},{"key":"ref59","first-page":"1697","article-title":"Seventy years beyond neural networks: Retrospect and prospect","volume":"39","author":"Jiao","year":"2016","journal-title":"Chin. J. Comput."},{"key":"ref60","volume-title":"Theory and Applications of Adaptive Multiscale Networks","author":"Jiao","year":"2008"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.02.003"},{"issue":"4","key":"ref62","first-page":"1201","article-title":"Deep learning for multi-scale object detection: A survey","volume":"32","author":"Chen","year":"2020","journal-title":"J. Softw."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.103910"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3005231"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3135248"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12042"},{"key":"ref67","volume-title":"Scale","year":"2023"},{"key":"ref68","volume-title":"Scale\u2014Wikipedia, The Free Encyclopedia","year":"2023"},{"key":"ref69","volume-title":"Wallpaper","year":"2023"},{"key":"ref70","volume-title":"Multi-Scale Space Concepts","year":"2019"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1959.sp006308"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1037\/13798-000"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1152\/ajplegacy.1938.121.2.400"},{"key":"ref74","volume-title":"Vision: A Computational Investigation Into the Human Representation and Processing of Visual Information","author":"Marr","year":"1982"},{"key":"ref75","volume-title":"Digital Picture Processing","author":"Rosenfeld","year":"1976"},{"key":"ref76","article-title":"Computer simulations of oriented multiple spatial frequency band coring","author":"Ogden","year":"1985"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1981.4308619"},{"key":"ref78","article-title":"The Gaussian derivative model for machine vision: Visual cortex simulation","author":"Young","year":"1986"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1163\/156856887x00222"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1163\/156856801753253582"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1163\/156856801753253591"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.14711\/spcol\/b458351"},{"key":"ref83","volume-title":"A First Course in Wavelets With Fourier Analysis","author":"Boggess","year":"2011"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/BF01456326"},{"key":"ref85","volume-title":"Wavelet Transform and Engineering Applications","author":"Peng","year":"1999"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/72.165591"},{"issue":"6","key":"ref87","first-page":"890","article-title":"An adaptive Ridgelet neural network model","volume":"32","author":"Yang","year":"2005","journal-title":"J. Xidian Univ."},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref90","first-page":"151","article-title":"Learning object-class segmentation with convolutional neural networks","volume-title":"Proc. ESANN","author":"Schulz"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298636"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298641"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298686"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.348"},{"key":"ref97","first-page":"1","article-title":"Pushing the boundaries of boundary detection using deep learning","volume-title":"Proc. ICLR","author":"Kokkinos"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.207"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref101","first-page":"9310","article-title":"SNIPER: Efficient multi-scale training","volume-title":"Proc. NeurIPS","volume":"31","author":"Singh"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3007412"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3118221"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3223212"},{"key":"ref105","article-title":"Some improvements on deep convolutional neural network based image classification","author":"Howard","year":"2013","journal-title":"arXiv:1312.5402"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-75988-8_28"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-97177-8_29"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/78.157290"},{"key":"ref110","first-page":"1","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref112","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. ICLR","author":"Yu"},{"key":"ref113","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","volume-title":"Proc. NeurIPS","volume":"29","author":"Dai"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947352"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.422"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00615"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.200"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.239"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2006.68"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref126","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref129","first-page":"1","article-title":"ParseNet: Looking wider to see better","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref130","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","volume-title":"Proc. MICCAI","author":"Ronneberger"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2802944"},{"key":"ref132","first-page":"6965","article-title":"A probabilistic U-Net for segmentation of ambiguous images","volume-title":"Proc. NeurIPS","volume":"31","author":"Kohl"},{"key":"ref133","first-page":"3","article-title":"UNet++: A nested U-Net architecture for medical image segmentation","volume-title":"Proc. DLMIA","author":"Zhou"},{"key":"ref134","first-page":"424","article-title":"3D U-Net: Learning dense volumetric segmentation from sparse annotation","volume-title":"Proc. MICCAI","author":"\u00c7i\u00e7ek"},{"key":"ref135","article-title":"Attention U-Net: Learning where to look for the pancreas","author":"Oktay","year":"2018","journal-title":"arXiv:1804.03999"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00105"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_5"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_32"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref144","first-page":"1","article-title":"Big-little Net: An efficient multi-scale feature representation for visual and speech recognition","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref145","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. NeurIPS","volume":"27","author":"Eigen"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref147","first-page":"14030","article-title":"Multi-scale separable network for ultra-high-definition video deblurring","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Deng"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.02325"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.522"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00720"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00334"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref157","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref159","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref166","first-page":"7281","article-title":"HRFormer: High-resolution Transformer for dense prediction","volume-title":"Proc. NeurIPS","author":"Yuan"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01178"},{"key":"ref169","first-page":"15475","article-title":"ResT: An efficient transformer for visual recognition","volume-title":"Proc. NeurIPS","author":"Zhang"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01587"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref177","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref178","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref179","volume-title":"OpenImages: A Public Dataset for Large-scale Multi-label and Multi-class Image Classification","author":"Krasin","year":"2017"},{"key":"ref180","article-title":"OverFeat: Integrated recognition, localization and detection using convolutional networks","author":"Sermanet","year":"2013","journal-title":"arXiv:1312.6229"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00601"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1063\/5.0186054"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10949581\/10507032.pdf?arnumber=10507032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:29Z","timestamp":1764959969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10507032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":183,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3389454","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}