{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:11:37Z","timestamp":1776057097347,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42090012"],"award-info":[{"award-number":["42090012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"03 Special Research and 5G Project of Jiangxi Province in China","award":["20212ABC03A09"],"award-info":[{"award-number":["20212ABC03A09"]}]},{"name":"Zhuhai Industry University Research Cooperation Project of China","award":["ZH22017001210098PWC"],"award-info":[{"award-number":["ZH22017001210098PWC"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1109\/tcsvt.2021.3138743","type":"journal-article","created":{"date-parts":[[2021,12,27]],"date-time":"2021-12-27T21:07:24Z","timestamp":1640639244000},"page":"4940-4952","source":"Crossref","is-referenced-by-count":8,"title":["BiCSNet: A Bidirectional Cross-Scale Backbone for Recognition and Localization"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2703-9258","authenticated-orcid":false,"given":"Song","family":"Peng","sequence":"first","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4587-6826","authenticated-orcid":false,"given":"Zhenfeng","family":"Shao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4323-382X","authenticated-orcid":false,"given":"Xiao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Geosciences, University of Arkansas, Fayetteville, AR, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6482-6712","authenticated-orcid":false,"given":"Yi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Amazon Web Services Inc., Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6080-9771","authenticated-orcid":false,"given":"Ruiqian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Surveying and Mapping, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junwei","family":"Zha","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Feature pyramid networks for object detection","volume-title":"arXiv:1612.03144","author":"Lin","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00720"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref4","article-title":"Feature pyramid grids","volume-title":"arXiv:2004.03580","author":"Chen","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"ref6","article-title":"DetectoRS: Detecting objects with recursive feature pyramid and switchable atrous convolution","volume-title":"arXiv:2006.02334","author":"Qiao","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978194"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3087002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01161"},{"key":"ref10","first-page":"760","article-title":"FishNet: A versatile backbone for image, region, and pixel level prediction","volume-title":"Proc. NeurIPS","author":"Sun"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1405.0312"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1706.05587"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00675"},{"key":"ref22","article-title":"Neural architecture search with reinforcement learning","volume-title":"arXiv:1611.01578","author":"Zoph","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2950526"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038649"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2909982"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2905373"},{"key":"ref27","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2015"},{"key":"ref28","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","volume-title":"arXiv:1704.04861","author":"Howard","year":"2017"},{"key":"ref29","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref33","article-title":"ResNeSt: Split-attention networks","volume-title":"arXiv:2004.08955","author":"Zhang","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2941017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063001"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref43","article-title":"DetNet: A backbone network for object detection","volume-title":"arXiv:1804.06215","author":"Li","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09825-6"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063377"},{"key":"ref46","article-title":"YOLOv4: Optimal speed and accuracy of object detection","volume-title":"arXiv:2004.10934","author":"Bochkovskiy","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01188"},{"key":"ref54","volume-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref57","article-title":"MMDetection: Open MMLab detection toolbox and benchmark","volume-title":"arXiv:1906.07155","author":"Chen","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref59","volume-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results","author":"Everingham","year":"2010"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref61","article-title":"Searching for activation functions","volume-title":"arXiv:1710.05941","author":"Ramachandran","year":"2017"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01161"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_34"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref68","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"arXiv:1511.07122","author":"Yu","year":"2015"},{"key":"ref69","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"arXiv:1510.00149","author":"Han","year":"2015"},{"key":"ref70","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"arXiv:2010.11929","author":"Dosovitskiy","year":"2020"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.3390\/rs12193140"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.08.002"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9849156\/09663310.pdf?arnumber=9663310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:37:01Z","timestamp":1704847021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9663310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8]]},"references-count":74,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2021.3138743","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8]]}}}