{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T08:14:43Z","timestamp":1774080883357,"version":"3.50.1"},"reference-count":91,"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":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L191004"],"award-info":[{"award-number":["L191004"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61271374"],"award-info":[{"award-number":["61271374"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2020.3013162","type":"journal-article","created":{"date-parts":[[2020,8,12]],"date-time":"2020-08-12T20:47:54Z","timestamp":1597265274000},"page":"8326-8338","source":"Crossref","is-referenced-by-count":187,"title":["MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object Segmentation"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5475-1473","authenticated-orcid":false,"given":"Tianfei","family":"Zhou","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8632-4334","authenticated-orcid":false,"given":"Jianwu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shunzhou","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5243-7189","authenticated-orcid":false,"given":"Ran","family":"Tao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2656-3082","authenticated-orcid":false,"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.189"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3391743"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_42"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref79","article-title":"The 2019 DAVIS challenge on VOS: Unsupervised multi-object segmentation","author":"caelles","year":"2019","journal-title":"arXiv 1905 00737"},{"key":"ref33","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"pont-tuset","year":"2017","journal-title":"arXiv 1704 00675"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_13"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00125"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.369"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7008"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366154"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"ref60","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.648"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00342"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.86"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.228"},{"key":"ref64","first-page":"155","article-title":"Saliency based on information maximization","author":"bruce","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref65","first-page":"545","article-title":"Graph-based visual saliency","author":"harel","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.15.3.419"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.81"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-3833-5_5"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"ref69","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2282897"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.47"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandl.2012.08.003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1401_3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1167\/13.9.144"},{"key":"ref24","author":"palmer","year":"1999","journal-title":"Vision Science Photons to phenomenology"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9280.2009.02471.x"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.64"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1037\/11496-005"},{"key":"ref50","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00936"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00147"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2936112"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777665"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00737"},{"key":"ref53","first-page":"715","article-title":"Pyramid dilated deeper convlstm for video salient object detection","author":"song","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126418"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.242"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754941"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.374"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247883"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.87"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00102"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00542"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794254"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00933"},{"key":"ref84","first-page":"565","article-title":"PReMVOS: Proposal-generation, refinement and merging for video object segmentation","author":"luiten","year":"2018","journal-title":"Proc ACCV"},{"key":"ref18","first-page":"1410","article-title":"Zero-shot learning with semantic output codes","author":"palatucci","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.784"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00248"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.79"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00432"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298961"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.223"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093285"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2662005"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.21"},{"key":"ref49","first-page":"1","article-title":"EpO-net: Exploiting geometric constraints on dense trajectories for motion saliency","author":"faisal","year":"2019","journal-title":"Proc IEEE Winter Conf Appl Comput Vis (WACV)"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref88","article-title":"Simple vs complex temporal recurrences for video saliency prediction","author":"linardos","year":"2019","journal-title":"arXiv 1907 01869"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_21"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2930152"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00683"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.480"},{"key":"ref47","article-title":"Video object segmentation with episodic graph memory networks","author":"lu","year":"2020","journal-title":"arXiv 2007 07020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_48"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00374"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1122-2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00318"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/09165947.pdf?arnumber=9165947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:38:41Z","timestamp":1651070321000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9165947\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.3013162","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}