{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T17:29:49Z","timestamp":1783445389383,"version":"3.54.6"},"reference-count":99,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grant Council of the Hong Kong SAR","award":["16201420"],"award-info":[{"award-number":["16201420"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tpami.2023.3246174","type":"journal-article","created":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T20:44:03Z","timestamp":1676666643000},"page":"10197-10211","source":"Crossref","is-referenced-by-count":32,"title":["Occlusion-Aware Instance Segmentation Via BiLayer Network Architectures"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0944-720X","authenticated-orcid":false,"given":"Lei","family":"Ke","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3148-0380","authenticated-orcid":false,"given":"Yu-Wing","family":"Tai","sequence":"additional","affiliation":[{"name":"HKUST and Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6495-3685","authenticated-orcid":false,"given":"Chi-Keung","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_31"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.308"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298969"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.479"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2303085"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.208"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00771"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.320"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995623"},{"key":"ref46","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"cheng","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_42"},{"key":"ref48","first-page":"399","article-title":"Symmetric stereo matching for occlusion handling","author":"sun","year":"2005","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref47","article-title":"Learning equivariant segmentation with instance-unique querying","author":"wang","year":"2022","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00707"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00437"},{"key":"ref43","article-title":"ISTR: End-to-end instance segmentation via transformers","author":"hu","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.305"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00313"},{"key":"ref7","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00146"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00422"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00657"},{"key":"ref40","first-page":"21898","article-title":"SOLQ: Segmenting objects by learning queries","author":"dong","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00928"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00131"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00433"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_42"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.378"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00940"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.305"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"ref38","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00745"},{"key":"ref23","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.472"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_42"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.774"},{"key":"ref27","article-title":"SOLO: Segmenting objects by locations","author":"wang","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.100"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.343"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.342"},{"key":"ref15","first-page":"109","article-title":"Efficient inference in fully connected CRFs with Gaussian edge potentials","author":"kr\u00e4henb\u00fchl","year":"2011","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.398"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_10"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01106"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"ref99","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"gu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00215"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00401"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"ref19","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"kolesnikov","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","first-page":"9626","article-title":"FCOS: Fully convolutional one-stage object detection","author":"tian","year":"2019","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00860"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00930"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00813"},{"key":"ref85","first-page":"1192","article-title":"Prototypical cross-attention networks for multiple object tracking and segmentation","author":"ke","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_39"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00098"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref83","article-title":"Occluded video instance segmentation","author":"qi","year":"2021"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref78","first-page":"936","article-title":"Feature pyramid networks for object detection","author":"lin","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref75","first-page":"254","article-title":"Dual graph convolutional network for semantic segmentation","author":"zhang","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"ref77","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref76","first-page":"9245","article-title":"Beyond grids: Learning graph representations for visual recognition","author":"li","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref73","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00322"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_5"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01073"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00643"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01420"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00384"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_9"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_39"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00811"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10169863\/10048550.pdf?arnumber=10048550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:44:12Z","timestamp":1689615852000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10048550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":99,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3246174","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":[[2023,8]]}}}