{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T17:17:19Z","timestamp":1790961439414,"version":"4.1.0"},"reference-count":122,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["4182056"],"award-info":[{"award-number":["4182056"]}]},{"name":"CCF-Tencent Open Fund"},{"name":"Tencent AI Lab Rhino-Bird Focused Research Program"},{"name":"Zhijiang Lab's International Talent Fund for Young Professionals"},{"name":"Beijing Municipal Education Commission."},{"name":"Yahoo Faculty Research and Engagement Program Award"},{"name":"Amazon AWS Machine Learning Research Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,7,1]]},"DOI":"10.1109\/tpami.2020.2966453","type":"journal-article","created":{"date-parts":[[2020,1,13]],"date-time":"2020-01-13T20:49:35Z","timestamp":1578948575000},"page":"2413-2428","source":"Crossref","is-referenced-by-count":110,"title":["Paying Attention to Video Object Pattern Understanding"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0802-9567","authenticated-orcid":false,"given":"Wenguan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2656-3082","authenticated-orcid":false,"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9543-6960","authenticated-orcid":false,"given":"Xiankai","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4584-3453","authenticated-orcid":false,"given":"Steven C. H.","family":"Hoi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4094-8413","authenticated-orcid":false,"given":"Haibin","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.87"},{"key":"ref38","first-page":"670","article-title":"Maximum weight cliques with mutex constraints for video object segmentation","author":"ma","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2481711"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.223"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247883"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126418"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.82"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.21"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.374"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995508"},{"key":"ref27","article-title":"The 2019 DAVIS challenge on VOS: Unsupervised multi-object segmentation","author":"caelles","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_21"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.15.3.419"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-010-9074-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/1073858413514136"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.407"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1080\/13506280444000661"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2819173"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2383320"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.55"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.43"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00933"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00542"},{"key":"ref59","article-title":"Salient object detection in the deep learning era: An in-depth survey","author":"wang","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2125450"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_27"},{"key":"ref56","first-page":"1664","article-title":"On the connections between saliency and tracking","author":"mahadevan","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2840724"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2267725"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_48"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2701279"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299035"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/34.683770"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF01420982"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238315"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2002.801448"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_22"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00374"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.242"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.64"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.228"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_13"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.81"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.784"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.107"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.480"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2662005"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2165292"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366154"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.834657"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.86"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1167\/8.7.32"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref75","author":"frackowiak","year":"2004","journal-title":"Human Brain Function"},{"key":"ref78","first-page":"481","article-title":"Discriminant saliency for visual recognition from cluttered scenes","author":"gao","year":"2005","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref79","first-page":"155","article-title":"Saliency based on information maximization","author":"bruce","year":"2006","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2336549"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2595324"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2308642"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_3"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754941"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00875"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00342"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1993.378191"},{"key":"ref69","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00318"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00449"},{"key":"ref107","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":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1122-2"},{"key":"ref92","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref105","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"shi","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref91","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1167\/7.13.14"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2013.07.016"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299055"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_46"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794254"},{"key":"ref98","article-title":"MIT saliency benchmark.","author":"bylinskii","year":"0"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_20"},{"key":"ref96","article-title":"A benchmark of computational models of saliency to predict human fixations","author":"judd","year":"2012","journal-title":"MIT Technical Report"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1167\/8.14.18"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.273"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2460013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298961"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.563"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.429"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.32"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2600594"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383267"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-3833-5_5"},{"key":"ref84","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TIP.2009.2030969","article-title":"A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression","volume":"19","author":"guo","year":"2010","journal-title":"IEEE Trans Image Process"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.698"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(80)90005-5"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2273613"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2905607"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00683"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.433"},{"key":"ref80","first-page":"545","article-title":"Graph-based visual saliency","author":"harel","year":"2007","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.31"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.58"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2936112"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref122","first-page":"565","article-title":"PReMVOS: Proposal-generation, refinement and merging for video object segmentation","author":"luiten","year":"2018","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref85","first-page":"681","article-title":"Dynamic visual attention: Searching for coding length increments","author":"hou","year":"2009","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1167\/9.12.15"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.71"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9448371\/08957473.pdf?arnumber=8957473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:14Z","timestamp":1652194154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8957473\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,1]]},"references-count":122,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.2966453","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":[[2021,7,1]]}}}