{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:10:04Z","timestamp":1775578204460,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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"}],"funder":[{"name":"ICT R&D program of MSIT\/IITP","award":["2017-0-01772"],"award-info":[{"award-number":["2017-0-01772"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,1,1]]},"DOI":"10.1109\/tpami.2020.3008917","type":"journal-article","created":{"date-parts":[[2020,7,13]],"date-time":"2020-07-13T22:22:52Z","timestamp":1594678972000},"page":"442-455","source":"Crossref","is-referenced-by-count":30,"title":["Space-Time Memory Networks for Video Object Segmentation With User Guidance"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8498-0864","authenticated-orcid":false,"given":"Seoung Wug","family":"Oh","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4822-855X","authenticated-orcid":false,"given":"Joon-Young","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8910-0937","authenticated-orcid":false,"given":"Ning","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8512-216X","authenticated-orcid":false,"given":"Seon Joo","family":"Kim","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","article-title":"The 2018 davis challenge on video object segmentation","author":"Caelles","year":"2018"},{"key":"ref2","first-page":"325","article-title":"MaskRNN: Instance level video object segmentation","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.238"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref11","first-page":"2440","article-title":"End-to-end memory networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref13","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kumar"},{"key":"ref14","article-title":"Interactive video object segmentation in the wild","author":"Benard","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00539"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref18","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref19","article-title":"A unified model for semi-supervised and interactive video object segmentation using space-time memory networks","volume-title":"Proc. Comput. Vis. Pattern Recognit. Conf.","author":"Oh"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01164-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00626"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00130"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00916"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00542"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.4324\/9780240817057"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925973"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073233"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459293"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531337"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015764"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.370"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366194"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.47"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.681"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.80"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00153"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00450"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-038"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465960"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref52","first-page":"1099","article-title":"Weakly-supervised disentangling with recurrent transformations for 3D view synthesis","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/62065.62074"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref55","article-title":"BoLTVOS: Box-level tracking for video object segmentation","author":"Voigtlaender","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_35"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.87"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.423"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.336"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.81"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00774"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_31"},{"key":"ref63","article-title":"The 2019 davis challenge on vos: Unsupervised multi-object segmentation","author":"Caelles","year":"2019"},{"key":"ref64","article-title":"Interactive video object segmentation using sparse-to-dense networks","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Heo"},{"key":"ref65","article-title":"Interactive video object segmentation via spatio-temporal context aggregation and online learning","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Lin"},{"key":"ref66","article-title":"Robust multiple object mask propagation with efficient object tracking","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Ren"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9639876\/09139391.pdf?arnumber=9139391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:23:15Z","timestamp":1704838995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9139391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,1]]},"references-count":66,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3008917","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":[[2022,1,1]]}}}