{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T17:06:45Z","timestamp":1785863205833,"version":"3.56.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2018YFC1704400"],"award-info":[{"award-number":["2018YFC1704400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811463"],"award-info":[{"award-number":["U1811463"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"UCAS Joint Ph.D. Training Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2019.2947806","type":"journal-article","created":{"date-parts":[[2019,10,22]],"date-time":"2019-10-22T19:59:31Z","timestamp":1571774371000},"page":"2078-2093","source":"Crossref","is-referenced-by-count":85,"title":["Mask SSD: An Effective Single-Stage Approach to Object Instance Segmentation"],"prefix":"10.1109","volume":"29","author":[{"given":"Hui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonglin","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2744-1191","authenticated-orcid":false,"given":"Kunfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wensheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9185-3989","authenticated-orcid":false,"given":"Fei-Yue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1990","article-title":"Learning to segment object candidates","author":"pinheiro","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.231"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.260"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref37","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref36","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.444"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref28","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":"ref64","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref27","article-title":"DSSD: Deconvolutional single shot detector","author":"fu","year":"2017","journal-title":"arXiv 1701 06659"},{"key":"ref65","article-title":"Beyond skip connections: Top-down modulation for object detection","author":"shrivastava","year":"2016","journal-title":"arXiv 1612 06851"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.84"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.342"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.343"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref25","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref50","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref59","first-page":"534","article-title":"Instance-sensitive fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.100"},{"key":"ref57","first-page":"1","article-title":"Bottom-up instance segmentation using deep higher-order CRFs","author":"arnab","year":"2016","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00609"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116636"},{"key":"ref53","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2158001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2736887"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298969"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1070-x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref17","article-title":"A review on deep learning techniques applied to semantic segmentation","author":"garcia-garcia","year":"2017","journal-title":"arXiv 1704 06857"},{"key":"ref18","first-page":"297","article-title":"Simultaneous detection and segmentation","author":"hariharan","year":"2014","journal-title":"Eur Conf Comput Vis"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.17"},{"key":"ref5","article-title":"Hands deep in deep learning for hand pose estimation","author":"oberweger","year":"2015","journal-title":"arXiv 1502 06807"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2815678"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2866435"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.378"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500621"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.472"},{"key":"ref44","first-page":"14","article-title":"Pixel-level encoding and depth layering for instance-level semantic labeling","author":"uhrig","year":"2016","journal-title":"Proc German Conf Pattern Recognit"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2775623"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/08879691.pdf?arnumber=8879691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:09Z","timestamp":1651070349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8879691\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tip.2019.2947806","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}