{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T15:57:58Z","timestamp":1785599878162,"version":"3.56.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["IIS-1546305"],"award-info":[{"award-number":["IIS-1546305"]}]},{"name":"NSF","award":["IIS-1637941"],"award-info":[{"award-number":["IIS-1637941"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,5,1]]},"DOI":"10.1109\/tpami.2019.2956516","type":"journal-article","created":{"date-parts":[[2019,11,28]],"date-time":"2019-11-28T22:30:13Z","timestamp":1574980213000},"page":"1483-1498","source":"Crossref","is-referenced-by-count":1626,"title":["Cascade R-CNN: High Quality Object Detection and Instance Segmentation"],"prefix":"10.1109","volume":"43","author":[{"given":"Zhaowei","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nuno","family":"Vasconcelos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"ref32","first-page":"765","article-title":"Cornernet: Detecting objects as paired keypoints","author":"law","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","first-page":"816","article-title":"Acquisition of localization confidence for accurate object detection","author":"jiang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref37","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref34","first-page":"339","article-title":"Detnet: Design backbone for object detection","author":"li","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref62","article-title":"A multipath network for object detection","author":"zagoruyko","year":"2016","journal-title":"Proc BMVC"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.305"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.474"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref29","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Int Conf Mach Learn"},{"key":"ref2","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref22","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","author":"girshick","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.650"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.126"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.75"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref55","first-page":"3","article-title":"Group normalization","author":"wu","year":"2018","journal-title":"Proc ECCV"},{"key":"ref54","article-title":"Single-shot bidirectional pyramid networks for high-quality object detection","author":"wu","year":"2018","journal-title":"CoRR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"ref11","first-page":"973","article-title":"The foundations of cost-sensitive learning","author":"elkan","year":"2001","journal-title":"Proc 17th Int Joint Conf Artif Intell"},{"key":"ref40","first-page":"643","article-title":"Learning efficient single-stage pedestrian detectors by asymptotic localization fitting","author":"liu","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59119-2_166"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.135"},{"key":"ref17","article-title":"Attend refine repeat: Active box proposal generation via in-out localization","author":"gidaris","year":"2016","journal-title":"Proc BMVC"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.92"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref4","first-page":"2887","article-title":"Face alignment by explicit shape regression","author":"cao","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.343"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref7","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540094"},{"key":"ref46","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.281"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.260"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.71"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00647"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.214"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/9393625\/8917599-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9393625\/08917599.pdf?arnumber=8917599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:21Z","timestamp":1652194161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8917599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,1]]},"references-count":64,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2956516","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,1]]}}}