{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T04:32:32Z","timestamp":1727065952085},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.00374","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T20:55:59Z","timestamp":1705352159000},"page":"4024-4033","source":"Crossref","is-referenced-by-count":10,"title":["High Quality Entity Segmentation"],"prefix":"10.1109","author":[{"given":"Lu","family":"Qi","sequence":"first","affiliation":[{"name":"The University of California,Merced"}]},{"given":"Jason","family":"Kuen","sequence":"additional","affiliation":[{"name":"Adobe Research"}]},{"given":"Tiancheng","family":"Shen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Jiuxiang","family":"Gu","sequence":"additional","affiliation":[{"name":"Adobe Research"}]},{"given":"Wenbo","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Weidong","family":"Guo","sequence":"additional","affiliation":[{"name":"Tencent,QQ Brower Lab"}]},{"given":"Jiaya","family":"Jia","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Zhe","family":"Lin","sequence":"additional","affiliation":[{"name":"Adobe Research"}]},{"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"The University of California,Merced"}]}],"member":"263","reference":[{"volume-title":"Pixabay","key":"ref1"},{"volume-title":"Unsplash","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"article-title":"Mask2former for video instance segmentation","year":"2021","author":"Cheng","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref8","article-title":"Per-pixel classification is not all you need for semantic segmentation","author":"Cheng","year":"2021","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.715"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"article-title":"Vita: Video instance segmentation via object token association","volume-title":"NeurlPS","author":"Heo","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00525"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00437"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00371","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"NeurIPS","author":"Krizhevsky"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130490"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200416"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00473"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"volume-title":"Vision: A computational investigation into the human representation and processing of visual information","year":"1982","author":"Marr","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00313"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01421"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3227513"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_3"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","volume-title":"NeurIPS Workshop","author":"Schuhmann","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793917"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01044"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"article-title":"Entity-level text-guided image manipulation","year":"2023","author":"Wang","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00478"},{"article-title":"Patchdct: Patch refinement for high quality instance segmentation","volume-title":"ICLR","author":"Wen","key":"ref56"},{"article-title":"Synscapes: A photorealistic synthetic dataset for street scene parsing","year":"2018","author":"Wrenninge","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240509"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.320"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","start":{"date-parts":[[2023,10,1]]},"location":"Paris, France","end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10377852.pdf?arnumber=10377852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:49:08Z","timestamp":1705542548000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10377852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51070.2023.00374","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}