{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T07:35:04Z","timestamp":1775720104203,"version":"3.50.1"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62192713"],"award-info":[{"award-number":["62192713"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62171380"],"award-info":[{"award-number":["62171380"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Industrial Innovation Chain Project in Industrial Domain of Shaanxi","award":["2022ZDLGY01-02"],"award-info":[{"award-number":["2022ZDLGY01-02"]}]},{"name":"Technology Industrialization Plan of Xi\u2019an","award":["XA2020-RGZNTJ-0076"],"award-info":[{"award-number":["XA2020-RGZNTJ-0076"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/tcsvt.2022.3198329","type":"journal-article","created":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T19:34:11Z","timestamp":1660246451000},"page":"242-256","source":"Crossref","is-referenced-by-count":18,"title":["Scale-Balanced Real-Time Object Detection With Varying Input-Image Resolution"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4018-2617","authenticated-orcid":false,"given":"Longbin","family":"Yan","sequence":"first","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3209-020X","authenticated-orcid":false,"given":"Yunxiao","family":"Qin","sequence":"additional","affiliation":[{"name":"Neuroscience and Intelligent Media Institute, Communication University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2306-8860","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref3","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref4","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv:1904.07850"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6838"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990070"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2772796"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2987465"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2981652"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2900709"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2905881"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2980876"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref18","first-page":"9310","article-title":"Sniper: Efficient multi-scale training","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Singh"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074273"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5121\/csit.2019.91713"},{"key":"ref22","article-title":"Stitcher: Feedback-driven data provider for object detection","author":"Chen","year":"2020","journal-title":"arXiv:2004.12432"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref27","article-title":"DenseBox: Unifying landmark localization with end to end object detection","author":"Huang","year":"2015","journal-title":"arXiv:1509.04874"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00093"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","article-title":"Learning spatial fusion for single-shot object detection","author":"Liu","year":"2019","journal-title":"arXiv:1911.09516"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref40","article-title":"MMDetection: Open MMLab detection toolbox and benchmark","author":"Chen","year":"2019","journal-title":"arXiv:1906.07155"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref43","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref44","volume-title":"Zylo117","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00310"},{"key":"ref46","first-page":"1","article-title":"Pix2seq: A language modeling framework for object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3067439"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3002345"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16374"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref52","article-title":"Micro-batch training with batch-channel normalization and weight standardization","author":"Qiao","year":"2019","journal-title":"arXiv:1903.10520"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3050494"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00975"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00308"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-11940-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.01.021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00657"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01053"},{"key":"ref65","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref66","first-page":"1","article-title":"VIDT: An efficient and effective fully transformer-based object detector","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref67","first-page":"26183","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"34","author":"Fang"},{"key":"ref68","first-page":"1","article-title":"GiraffeDet: A heavy-neck paradigm for object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tan"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref70","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Li"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00679"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475351"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref78","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref79","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"29","author":"Dai"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10007626\/09855518.pdf?arnumber=9855518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T05:04:46Z","timestamp":1709355886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9855518\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":79,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3198329","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}