{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:51:46Z","timestamp":1775069506510,"version":"3.50.1"},"reference-count":93,"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":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["4182056"],"award-info":[{"award-number":["4182056"]}],"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":["61602183"],"award-info":[{"award-number":["61602183"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Open Fund"},{"name":"Zhijiang Lab\u2019s International Talent Fund for Young Professionals"},{"name":"Fok Ying-Tong Education Foundation for Young Teachers"},{"DOI":"10.13039\/501100002888","name":"Beijing Municipal Commission of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002888","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.2019.2936112","type":"journal-article","created":{"date-parts":[[2019,8,23]],"date-time":"2019-08-23T20:03:22Z","timestamp":1566590602000},"page":"1113-1126","source":"Crossref","is-referenced-by-count":132,"title":["Video Saliency Prediction Using Spatiotemporal Residual Attentive Networks"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6872-5540","authenticated-orcid":false,"given":"Qiuxia","family":"Lai","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0802-9567","authenticated-orcid":false,"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3244-4111","authenticated-orcid":false,"given":"Hanqiu","family":"Sun","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","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc Artif Intell Statist"},{"key":"ref72","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"shi","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2851672"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2616302"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1167\/9.7.4"},{"key":"ref39","article-title":"Salient object detection in the deep learning era: An in-depth survey","author":"wang","year":"2019","journal-title":"arXiv 1904 09146"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.98"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2840724"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref79","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2910377"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2662005"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2460013"},{"key":"ref30","first-page":"1","article-title":"Contrast prior and fluid pyramid integration for rgbd salient object detection","author":"zhao","year":"2019","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2763819"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00875"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754941"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.338"},{"key":"ref28","first-page":"186","article-title":"Salient objects in clutter: Bringing salient object detection to the foreground","author":"fan","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00318"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00154"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296851"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2722691"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2595324"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2829605"},{"key":"ref24","article-title":"Delving deeper into convolutional networks for learning video representations","author":"ballas","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref23","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-010-9074-z"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366154"},{"key":"ref50","first-page":"1063","article-title":"Video saliency detection via dynamic consistent spatio-temporal attention modelling","author":"zhong","year":"2013","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.429"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(02)00016-0"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2273613"},{"key":"ref59","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref58","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":"ref57","article-title":"Recurrent mixture density network for spatiotemporal visual attention","author":"bazzani","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2628583"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2336549"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2277884"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299189"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2795740"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2710620"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487833"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2817047"},{"key":"ref13","first-page":"64","article-title":"Realistic avatar eye and head animation using a neurobiological model of visual attention","volume":"5200","author":"itti","year":"2003","journal-title":"Proc Appl Sci Neural Netw Fuzzy Syst Evol Comput"},{"key":"ref14","first-page":"2944","article-title":"SUNDAY: Saliency using natural statistics for dynamic analysis of scenes","author":"zhang","year":"2009","journal-title":"Proc AAAI Annu Cognit Sci Conf"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2259837"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.152"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601784"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1167\/9.12.15"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2567391"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777665"},{"key":"ref83","first-page":"681","article-title":"Dynamic visual attention: Searching for coding length increments","author":"hou","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","first-page":"602","article-title":"DeepVS: A deep learning based video saliency prediction approach","author":"jiang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref80","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":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS.2009.165"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2267205"},{"key":"ref3","article-title":"Inferring salient objects from human fixations","author":"wang","year":"0","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.358"},{"key":"ref85","first-page":"426","article-title":"A new perceived motion based shot content representation","author":"ma","year":"2001","journal-title":"Proc Int Conf Image Process"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.71"},{"key":"ref86","first-page":"1","article-title":"A model of motion attention for video skimming","author":"ma","year":"2002","journal-title":"Proc Int Conf Image Process"},{"key":"ref7","first-page":"362","article-title":"Predicting eye fixations using convolutional neural networks","author":"liu","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref49","first-page":"545","article-title":"Graph-based visual saliency","author":"harel","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2003.1221571"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326506"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1109\/TNNLS.2016.2628878","article-title":"Learning to predict eye fixations via multiresolution convolutional neural networks","volume":"29","author":"liu","year":"2016","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.445"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref48","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383267"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1167\/8.7.32"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.86"},{"key":"ref44","first-page":"155","article-title":"Saliency based on information maximization","author":"bruce","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","first-page":"481","article-title":"Discriminant saliency for visual recognition from cluttered scenes","author":"gao","year":"2005","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/08811731.pdf?arnumber=8811731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:04Z","timestamp":1651070344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8811731\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":93,"URL":"https:\/\/doi.org\/10.1109\/tip.2019.2936112","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}