{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:22:03Z","timestamp":1782318123978,"version":"3.54.5"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpami.2022.3227513","type":"journal-article","created":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T18:39:23Z","timestamp":1670524763000},"page":"1-14","source":"Crossref","is-referenced-by-count":42,"title":["Open World Entity Segmentation"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2684-0062","authenticated-orcid":false,"given":"Lu","family":"Qi","sequence":"first","affiliation":[{"name":"Department of CSE, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Kuen","sequence":"additional","affiliation":[{"name":"Adobe Research, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab., China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiuxiang","family":"Gu","sequence":"additional","affiliation":[{"name":"Adobe Research, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengshuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip","family":"Torr","sequence":"additional","affiliation":[{"name":"Department of Engineering Science, University of Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1154-9907","authenticated-orcid":false,"given":"Zhe","family":"Lin","sequence":"additional","affiliation":[{"name":"Adobe Research, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1246-553X","authenticated-orcid":false,"given":"Jiaya","family":"Jia","sequence":"additional","affiliation":[{"name":"Department of CSE, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.343"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01421"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00313"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3085295"},{"key":"ref14","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref58","first-page":"2053","article-title":"Sequential context encoding for duplicate removal","author":"qi","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463191"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref11","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","author":"cheng","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref55","first-page":"1990","article-title":"Learning to segment object candidates","author":"pinheiro","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref10","first-page":"561","article-title":"Bi-directional cross-modality feature propagation with separation-and-aggregation gate for RGB-D semantic segmentation","author":"chen","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882269"},{"key":"ref17","article-title":"Infant categorization development","author":"davis","year":"0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185578"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2377715"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093355"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref51","author":"marr","year":"1982","journal-title":"Vision A Computational Investigation into the Human Representation and Processing of Visual Information"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref46","first-page":"9628","article-title":"An intriguing failing of convolutional neural networks and the CoordConv solution","author":"liu","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00633"},{"key":"ref89","first-page":"10326","article-title":"K-net: Towards unified image segmentation","author":"zhang","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00199"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref43","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref8","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017"},{"key":"ref7","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref9","first-page":"833","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0149-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00544"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487833"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_33"},{"key":"ref81","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","author":"xie","year":"2022","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00028"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01243"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00902"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"ref35","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref79","first-page":"329","article-title":"Image inpainting via generative multi-column convolutional neural networks","author":"wang","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref78","article-title":"SOLOv2: Dynamic and fast instance segmentation","author":"wang","year":"2020","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.58"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015780"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.271"},{"key":"ref75","article-title":"High-resolution image synthesis and semantic manipulation with conditional GANs","author":"wang","year":"2017"},{"key":"ref30","first-page":"667","article-title":"Dynamic filter networks","author":"jia","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-08849-y"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540226"},{"key":"ref39","article-title":"Fully convolutional networks for panoptic segmentation with point-based supervision","author":"li","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.472"},{"key":"ref71","author":"szeliski","year":"2010","journal-title":"Computer Vision Algorithms and Applications"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref73","first-page":"9626","article-title":"FCOS: Fully convolutional one-stage object detection","author":"tian","year":"2019","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073274"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00445"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref64","article-title":"FrankMocap: Fast monocular 3D hand and body motion capture by regression and integration","author":"rong","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00544"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref66","article-title":"Human detection, tracking and segmentation in surveillance video","author":"shu","year":"2014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00096"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00766"},{"key":"ref62","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref61","first-page":"547","article-title":"Zero-shot object detection: Learning to simultaneously recognize and localize novel concepts","author":"rahman","year":"2018","journal-title":"Proc Asian Conf Comput Vis"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09976289.pdf?arnumber=9976289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T00:02:24Z","timestamp":1686096144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9976289\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3227513","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":[[2022]]}}}