{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:48:56Z","timestamp":1772905736933,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2018,9,1]],"date-time":"2018-09-01T00:00:00Z","timestamp":1535760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Natural Key R&D Program of China","award":["2017YFB1002400"],"award-info":[{"award-number":["2017YFB1002400"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC projects","doi-asserted-by":"publisher","award":["61573037"],"award-info":[{"award-number":["61573037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004806","name":"Fok Ying-Tong Education Foundation","doi-asserted-by":"crossref","award":["151061"],"award-info":[{"award-number":["151061"]}],"id":[{"id":"10.13039\/501100004806","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Zhejiang Public Welfare Research Program","award":["2016C31062"],"award-info":[{"award-number":["2016C31062"]}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LY16F010004"],"award-info":[{"award-number":["LY16F010004"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/tip.2018.2837106","type":"journal-article","created":{"date-parts":[[2018,5,16]],"date-time":"2018-05-16T19:05:38Z","timestamp":1526497538000},"page":"4529-4544","source":"Crossref","is-referenced-by-count":19,"title":["Find Who to Look at: Turning From Action to Saliency"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0277-3301","authenticated-orcid":false,"given":"Mai","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roland","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.332"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0071569"},{"key":"ref33","author":"wang","year":"2017","journal-title":"Deep learning for video saliency detection"},{"key":"ref32","author":"bazzani","year":"2016","journal-title":"Recurrent mixture density network for spatiotemporal visual attention"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383337"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502128"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1080\/13506285.2013.849785"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1167\/14.8.5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025219"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362640"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2015.04.011"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2010.07.001"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221192"},{"key":"ref63","first-page":"53","year":"2002","journal-title":"Methodology for the Subjective Assessment of the Quality of Television Pictures"},{"key":"ref28","first-page":"1","article-title":"A probabilistic saliency model with memory-guided top-down cues for free-viewing","author":"hua","year":"2013","journal-title":"Proc Int Conf Multimedia Expo (ICME)"},{"key":"ref27","first-page":"1073","article-title":"A stochastic model of selective visual attention with a dynamic bayesian network","author":"pang","year":"2008","journal-title":"Proc Int Conf Multimedia Expo (ICME)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.152"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref1","author":"buswell","year":"1935","journal-title":"How People Look at Pictures A Study of The Psychology of Perception in Art"},{"key":"ref20","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 (NIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.445"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1167\/11.3.9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-012-9146-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70090-8_1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.62"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2009262"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2013.171"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2336550"},{"key":"ref58","author":"bylinskii","year":"2016","journal-title":"What do different evaluation metrics tell us about saliency models?"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.30"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1973.9030"},{"key":"ref54","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995676"},{"key":"ref52","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.05.023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396290"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299189"},{"key":"ref13","first-page":"545","article-title":"Graph-based visual saliency","author":"harel","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2007.06.015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0215-3"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2628583"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1882262.1866186"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206540"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2014.2314864"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2011.942473"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.834657"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000011205.11775.fd"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2008.09.007"},{"key":"ref46","first-page":"2879","article-title":"Face detection, pose estimation, and landmark localization in the wild","author":"zhu","year":"2012","journal-title":"Proc Comput Vis Pattern Recognit (CVPR)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/089976606774841602"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.218"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2015.7457929"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.16910\/jemr.7.2.5","article-title":"Influence of number, location and size of faces on gaze in video","volume":"7","author":"rahman","year":"2014","journal-title":"J Eye Movement Res"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/03610918208812265"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1167\/9.7.4"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1167\/7.14.4"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8370367\/08360155.pdf?arnumber=8360155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T20:16:40Z","timestamp":1661285800000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8360155\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":63,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tip.2018.2837106","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9]]}}}