{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:15:00Z","timestamp":1775578500230,"version":"3.50.1"},"reference-count":100,"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":[{"DOI":"10.13039\/501100001809","name":"Chinese National Natural Science Foundation Projects","doi-asserted-by":"publisher","award":["#61872367"],"award-info":[{"award-number":["#61872367"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Chinese National Natural Science Foundation Projects","doi-asserted-by":"publisher","award":["#61876178"],"award-info":[{"award-number":["#61876178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Chinese National Natural Science Foundation Projects","doi-asserted-by":"publisher","award":["#61806196"],"award-info":[{"award-number":["#61806196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Chinese National Natural Science Foundation Projects","doi-asserted-by":"publisher","award":["#61806203"],"award-info":[{"award-number":["#61806203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Chinese National Natural Science Foundation Projects","doi-asserted-by":"publisher","award":["#61976229"],"award-info":[{"award-number":["#61976229"]}],"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.2020.2986402","type":"journal-article","created":{"date-parts":[[2020,4,7]],"date-time":"2020-04-07T22:02:49Z","timestamp":1586296969000},"page":"674-687","source":"Crossref","is-referenced-by-count":107,"title":["RefineDet++: Single-Shot Refinement Neural Network for Object Detection"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3109-5770","authenticated-orcid":false,"given":"Shifeng","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Longyin","family":"Wen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[]},{"given":"Stan Z.","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.260"},{"key":"ref33","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"Proc ECCV"},{"key":"ref32","first-page":"75","article-title":"Learning to refine object segments","author":"pinheiro","year":"2016","journal-title":"Proc ECCV"},{"key":"ref31","first-page":"1990","article-title":"Learning to segment object candidates","author":"pinheiro","year":"2015","journal-title":"NIPS"},{"key":"ref30","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"2014","journal-title":"ECCV"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2730258"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.444"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2938879"},{"key":"ref28","first-page":"234","article-title":"Parallel feature pyramid network for object detection","author":"kim","year":"2018","journal-title":"Proc ECCV"},{"key":"ref27","first-page":"385","article-title":"Receptive field block net for accurate and fast object detection","author":"liu","year":"2018","journal-title":"Proc ECCV"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.212"},{"key":"ref21","article-title":"DSSD: Deconvolutional single shot detector","author":"fu","year":"2017","journal-title":"arXiv 1701 06659"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00062"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00237"},{"key":"ref26","first-page":"169","article-title":"Deep feature pyramid reconfiguration for object detection","author":"kong","year":"2018","journal-title":"Proc ECCV"},{"key":"ref100","first-page":"340","article-title":"Diagnosing error in object detectors","author":"hoiem","year":"2012","journal-title":"Proc ECCV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00609"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00094"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00657"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876304"},{"key":"ref57","first-page":"370","article-title":"Weakly supervised region proposal network and object detection","author":"tang","year":"2018","journal-title":"Proc ECCV"},{"key":"ref56","article-title":"Foveabox: Beyond anchor-based object detector","author":"kong","year":"2019","journal-title":"arXiv 1904 03797"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00093"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00975"},{"key":"ref52","article-title":"Objects as points","author":"zhou","year":"2019","journal-title":"arXiv 1904 07850"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.324"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref3","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc ECCV"},{"key":"ref6","first-page":"387","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref8","first-page":"657","article-title":"Occlusion-aware R-CNN: Detecting pedestrians in a crowd","author":"zhang","year":"2018","journal-title":"Proc ECCV"},{"key":"ref49","first-page":"734","article-title":"Cornernet: Detecting objects as paired keypoints","author":"law","year":"2018","journal-title":"Proc ECCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref46","first-page":"354","article-title":"A unified multi-scale deep convolutional neural network for fast object detection","author":"cai","year":"2016","journal-title":"Proc ECCV"},{"key":"ref45","first-page":"354","article-title":"Gated bi-directional CNN for object detection","author":"zeng","year":"2016","journal-title":"Proc ECCV"},{"key":"ref48","article-title":"Beyond skip connections: Top-down modulation for object detection","author":"shrivastava","year":"2016","journal-title":"arXiv 1612 06851"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.98"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.305"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_20"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.135"},{"key":"ref73","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFS","author":"chen","year":"2015","journal-title":"Proc ICLR"},{"key":"ref72","first-page":"116","article-title":"Shufflenet V2: Practical guidelines for efficient CNN architecture design","author":"ma","year":"2018","journal-title":"Proc ECCV"},{"key":"ref71","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref70","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc AAAI"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.01.012"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2017.8272675"},{"key":"ref74","article-title":"Parsenet: Looking wider to see better","author":"liu","year":"2016","journal-title":"Proc ICLR Workshop"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-69923-3_1"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.064"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01159-3"},{"key":"ref60","article-title":"Single pixel reconstruction for one-stage instance segmentation","author":"yao","year":"2019","journal-title":"arXiv 1904 07426"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref66","article-title":"Dual refinement network for single-shot object detection","author":"chen","year":"2018","journal-title":"arXiv 1807 08638"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref68","article-title":"Some improvements on deep convolutional neural network based image classification","author":"howard","year":"2013","journal-title":"ArXiv 1312 5402"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref69","first-page":"1","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref94","first-page":"339","article-title":"DetNet: Design backbone for object detection","author":"li","year":"2018","journal-title":"Proc ECCV"},{"key":"ref93","first-page":"392","article-title":"Learning region features for object detection","author":"gu","year":"2018","journal-title":"Proc ECCV"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00308"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00719"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00754"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref96","first-page":"210","article-title":"SOD-MTGAN: Small object detection via multi-task generative adversarial network","author":"bai","year":"2018","journal-title":"ECCV"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.557"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2875449"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref14","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref15","first-page":"192","article-title":"S3FD: Single shot scale-invariant face detector","author":"zhang","year":"2017","journal-title":"Proc ICCV"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref82","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"goyal","year":"2017","journal-title":"arXiv 1706 02677"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref81","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00136"},{"key":"ref19","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2014","journal-title":"Proc ICLR"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00730"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.276"},{"key":"ref89","first-page":"798","article-title":"Deep regionlets for object detection","author":"xu","year":"2018","journal-title":"Proc ECCV"},{"key":"ref85","first-page":"74","article-title":"Context refinement for object detection","author":"chen","year":"2018","journal-title":"Proc ECCV"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00435"},{"key":"ref87","first-page":"453","article-title":"Revisiting RCNN: On awakening the classification power of faster RCNN","author":"cheng","year":"2018","journal-title":"Proc ECCV"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9346111\/09058700.pdf?arnumber=9058700","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:30Z","timestamp":1652194230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9058700\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":100,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.2986402","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}