{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:02:20Z","timestamp":1772910140384,"version":"3.50.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036005"],"award-info":[{"award-number":["62036005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771348"],"award-info":[{"award-number":["61771348"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015803","name":"Grant from Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2020.3036749","type":"journal-article","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T21:26:50Z","timestamp":1605734810000},"page":"572-587","source":"Crossref","is-referenced-by-count":29,"title":["A Spatial-Temporal Recurrent Neural Network for Video Saliency Prediction"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9111-0499","authenticated-orcid":false,"given":"Kao","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7882-1066","authenticated-orcid":false,"given":"Zhenzhong","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Shan","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/110"},{"key":"ref72","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref71","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2165292"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2662005"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2005.03.019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2460013"},{"key":"ref78","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2210727"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754941"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2761361"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.04.062"},{"key":"ref37","article-title":"Salient object detection in the deep learning era: An in-depth survey","author":"wang","year":"2019","journal-title":"arXiv 1904 09146"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996406"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2567393"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00875"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.249"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2046270"},{"key":"ref61","first-page":"1568","article-title":"State-frequency memory recurrent neural networks","author":"hu","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00733"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601784"},{"key":"ref65","first-page":"7251","article-title":"Unflow: Unsupervised learning of optical flow with a bidirectional census loss","author":"meister","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00887"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-010-9074-z"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1117\/12.348467"},{"key":"ref69","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/135062800394667"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00783"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777665"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2883305"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(92)90344-8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2851672"},{"key":"ref51","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00248"},{"key":"ref58","first-page":"1","article-title":"Simple vs complex temporal recurrences for video saliency prediction","author":"linardos","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref57","first-page":"547","article-title":"Bayesian surprise attracts human attention","author":"itti","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1167\/9.12.15"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4124-5"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2273613"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-2802-3"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299189"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2990341"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00907"},{"key":"ref40","first-page":"155","article-title":"Saliency based on information maximization","author":"bruce","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2080279"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2282897"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(80)90005-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0215-3"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.118"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2336549"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.147"},{"key":"ref17","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2935715"},{"key":"ref83","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref19","first-page":"1","article-title":"Recurrent mixture density network for spatiotemporal visual attention","author":"bazzani","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1167\/8.7.32"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2567391"},{"key":"ref3","first-page":"545","article-title":"Graph-based visual saliency","author":"harel","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2936112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2991523"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2600594"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.513"},{"key":"ref45","first-page":"1","article-title":"Deep gaze i: Boosting saliency prediction with feature maps trained on imageNet","author":"kummerer","year":"2015","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2710620"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900174"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2473844"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.358"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247706"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09263359.pdf?arnumber=9263359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:07Z","timestamp":1652194267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9263359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.3036749","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}