{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T08:46:27Z","timestamp":1782463587555,"version":"3.54.5"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Innovation 2030-Major Project of Artificial Intelligence of the Ministry of Science and Technology of China","award":["2018AAA01028"],"award-info":[{"award-number":["2018AAA01028"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61632018"],"award-info":[{"award-number":["61632018"]}],"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":["61906131"],"award-info":[{"award-number":["61906131"]}],"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":["61936014"],"award-info":[{"award-number":["61936014"]}],"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":["61871470"],"award-info":[{"award-number":["61871470"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Post-Doctoral Program for Innovative Talents","award":["BX20180214"],"award-info":[{"award-number":["BX20180214"]}]},{"DOI":"10.13039\/501100002858","name":"China Post-Doctoral Science Foundation","doi-asserted-by":"publisher","award":["2018M641647"],"award-info":[{"award-number":["2018M641647"]}],"id":[{"id":"10.13039\/501100002858","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":[[2020,10]]},"DOI":"10.1109\/tcsvt.2019.2950526","type":"journal-article","created":{"date-parts":[[2019,10,30]],"date-time":"2019-10-30T20:26:03Z","timestamp":1572467163000},"page":"3372-3386","source":"Crossref","is-referenced-by-count":78,"title":["High-Level Semantic Networks for Multi-Scale Object Detection"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5160-6841","authenticated-orcid":false,"given":"Jiale","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6109-2522","authenticated-orcid":false,"given":"Shengjie","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.108"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.324"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00811"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.234"},{"key":"ref77","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_20"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.18"},{"key":"ref38","first-page":"784","article-title":"Acquisition of localization confidence for accurate object detection","author":"jiang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.15"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.166"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299034"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2648850"},{"key":"ref34","article-title":"Squeeze-and-excitation networks","author":"hu","year":"2017","journal-title":"arXiv 1709 01507"},{"key":"ref60","article-title":"Beyond skip connections: Top-down modulation for object detection","author":"shrivastava","year":"2016","journal-title":"arXiv 1612 06851"},{"key":"ref62","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref28","author":"girshick","year":"2018","journal-title":"Detectron"},{"key":"ref64","first-page":"1","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9497-0"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.221"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.207"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299143"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00136"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.259"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.91"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.111"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"ref24","article-title":"DSSD: Deconvolutional single shot detector","author":"fu","year":"2017","journal-title":"arXiv 1701 06659"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref50","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.639"},{"key":"ref59","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":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.87"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2630731"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2676130"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2601438"},{"key":"ref53","first-page":"424","article-title":"Local decorrelation for improved pedestrian detection","author":"nam","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.522"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2694224"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.557"},{"key":"ref12","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.236"},{"key":"ref14","first-page":"424","article-title":"3D object proposals for accurate object class detection","author":"chen","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2730258"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298784"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.141"},{"key":"ref17","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":"ref84","first-page":"192","article-title":"S3FD: Single shot scale-invariant face detector","author":"zhang","year":"2017","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.474"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2300479"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_17"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00740"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248017"},{"key":"ref6","first-page":"354","article-title":"A unified multi-scale deep convolutional neural network for fast object detection","author":"cai","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref85","first-page":"637","article-title":"Occlusion-aware R-CNN: Detecting pedestrians in a crowd","author":"zhang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2609807"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.384"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref87","first-page":"416","article-title":"Scale-adaptive deconvolutional regression network for pedestrian detection","author":"zhu","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.444"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00757"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2759508"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00615"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref47","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"arXiv 1405 0312"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref41","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2778227"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9210915\/08887288.pdf?arnumber=8887288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:29Z","timestamp":1651070369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8887288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":89,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2019.2950526","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}