{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T22:40:52Z","timestamp":1790808052695,"version":"4.1.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/tip.2018.2851672","type":"journal-article","created":{"date-parts":[[2018,6,29]],"date-time":"2018-06-29T18:48:02Z","timestamp":1530298082000},"page":"5142-5154","source":"Crossref","is-referenced-by-count":483,"title":["Predicting Human Eye Fixations via an LSTM-Based Saliency Attentive Model"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9640-9385","authenticated-orcid":false,"given":"Marcella","family":"Cornia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5125-4957","authenticated-orcid":false,"given":"Lorenzo","family":"Baraldi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Serra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.118"},{"key":"ref72","first-page":"26","article-title":"RMSProp: Divide the gradient by a running average of its recent magnitude","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Mach Learn"},{"key":"ref71","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref70","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_49"},{"key":"ref39","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":"ref38","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref33","first-page":"241","article-title":"Predicting human gaze using low-level saliency combined with face detection","author":"cerf","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995506"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1167\/13.4.11"},{"key":"ref30","first-page":"155","article-title":"Saliency based on information maximization","author":"bruce","year":"2005","journal-title":"Proc 18th Int Conf Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2273613"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2199126"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247706"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1167\/11.3.9"},{"key":"ref60","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2005.03.019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"ref63","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref64","article-title":"A benchmark of computational models of saliency to predict human fixations","author":"judd","year":"2012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(80)90005-5"},{"key":"ref65","author":"bylinskii","year":"2018","journal-title":"MIT Saliency Benchmark"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.147"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-3833-5_5"},{"key":"ref67","author":"bylinskii","year":"2016","journal-title":"What do different evaluation metrics tell us about saliency models?"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1510393112"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1149488.1149499"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/135062800394667"},{"key":"ref20","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2710620"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","author":"liu","year":"2016","journal-title":"A deep spatial contextual long-term recurrent convolutional network for saliency detection"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.71"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.513"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.358"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298731"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.399"},{"key":"ref59","author":"borji","year":"2015","journal-title":"Cat2000 A large scale fixation dataset for boosting saliency research"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1167\/9.7.4"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1167\/7.14.4"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.500"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.26"},{"key":"ref11","article-title":"Deep gaze I: Boosting saliency prediction with feature maps trained on ImageNet","author":"k\u00fcmmerer","year":"2015","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.620"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900174"},{"key":"ref15","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":"ref16","author":"gregor","year":"2015","journal-title":"Draw A recurrent neural network for image generation"},{"key":"ref17","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2282897"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36181-2_47"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3177745"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.98"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.272"},{"key":"ref7","first-page":"545","article-title":"Graph-based visual saliency","author":"harel","year":"2006","journal-title":"Proc 19th Int Conf Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298918"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_33"},{"key":"ref45","author":"dodge","year":"2017","journal-title":"Visual saliency prediction using a mixture of deep neural networks"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298938"},{"key":"ref47","first-page":"5455","article-title":"Visual saliency based on multiscale deep features","author":"li","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.623"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref44","author":"pan","year":"2017","journal-title":"Salgan Visual saliency prediction with generative adversarial networks"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.03.018"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8396881\/08400593.pdf?arnumber=8400593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:15:56Z","timestamp":1642004156000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8400593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":74,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tip.2018.2851672","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10]]}}}