{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:04:38Z","timestamp":1777655078526,"version":"3.51.4"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2019YFB1310300"],"award-info":[{"award-number":["2019YFB1310300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61633004"],"award-info":[{"award-number":["61633004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1109\/tcsvt.2020.2980876","type":"journal-article","created":{"date-parts":[[2020,3,17]],"date-time":"2020-03-17T02:46:35Z","timestamp":1584413195000},"page":"594-607","source":"Crossref","is-referenced-by-count":60,"title":["Joint Anchor-Feature Refinement for Real-Time Accurate Object Detection in Images and Videos"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3627-0371","authenticated-orcid":false,"given":"Xingyu","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6347-572X","authenticated-orcid":false,"given":"Junzhi","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6714-1313","authenticated-orcid":false,"given":"Shihan","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2338-5217","authenticated-orcid":false,"given":"Zhengxing","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1498-3103","authenticated-orcid":false,"given":"Li","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref38","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref32","article-title":"Objects as points","author":"zhou","year":"2019","journal-title":"arXiv 1904 07850"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00094"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00308"},{"key":"ref36","first-page":"1","article-title":"Cascade RetinaNet: Maintaining consistency for single-stage object detection","author":"zhang","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2508603"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00753"},{"key":"ref12","article-title":"Towards high performance video object detection for mobiles","author":"zhu","year":"2018","journal-title":"arXiv 1804 05830"},{"key":"ref13","first-page":"342","article-title":"Object detection in video with spatiotemporal sampling networks","author":"bertasius","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref14","first-page":"494","article-title":"Video object detection with an aligned spatial-temporal memory","author":"xiao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00596"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2894261"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.101"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.212"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref27","first-page":"404","article-title":"Receptive field block net for accurate and fast object detection","author":"liu","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref3","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref29","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref5","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736553"},{"key":"ref7","article-title":"Seq-NMS for video object detection","author":"han","year":"2016","journal-title":"arXiv 1602 08465"},{"key":"ref2","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.330"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref20","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018231"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2865280"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2926164"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.444"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref41","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref44","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref43","first-page":"4898","article-title":"Understanding the effective receptive field in deep convolutional neural networks","author":"luo","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","article-title":"DSSD: Deconvolutional single shot detector","author":"fu","year":"2017","journal-title":"arXiv 1701 06659"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9346111\/09037090.pdf?arnumber=9037090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:29Z","timestamp":1652194229000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9037090\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":47,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.2980876","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}