{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:12:39Z","timestamp":1781622759213,"version":"3.54.5"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":["61573037"],"award-info":[{"award-number":["61573037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010261","name":"Fok Ying Tung Education Foundation","doi-asserted-by":"publisher","award":["151061"],"award-info":[{"award-number":["151061"]}],"id":[{"id":"10.13039\/501100010261","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2019,11,1]]},"DOI":"10.1109\/tpami.2018.2858783","type":"journal-article","created":{"date-parts":[[2018,7,25]],"date-time":"2018-07-25T00:00:55Z","timestamp":1532476855000},"page":"2693-2708","source":"Crossref","is-referenced-by-count":211,"title":["Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0277-3301","authenticated-orcid":false,"given":"Mai","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7999-0291","authenticated-orcid":false,"given":"Yuhang","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7025-3626","authenticated-orcid":false,"given":"Jianyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9591-2568","authenticated-orcid":false,"given":"Minglang","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangyu","family":"Huo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zulin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.401"},{"key":"ref38","first-page":"1552","article-title":"What are we looking for: Towards statistical modeling of saccadic eye movements and visual saliency","author":"sun","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777665"},{"key":"ref32","first-page":"1","article-title":"SalGAN: Visual saliency prediction with generative adversarial networks","author":"pan","year":"2017","journal-title":"Proc Comput Vis Pattern Recog Workshop"},{"key":"ref31","article-title":"Recurrent mixture density network for spatiotemporal visual attention","author":"bazzani","year":"2017","journal-title":"Int Conf on Learning Representations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_50"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995423"},{"key":"ref36","first-page":"1","article-title":"Predicting the driver's focus of attention: The DR(eye)VE project","author":"calderara","year":"2017","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.513"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754941"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2710620"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.358"},{"key":"ref29","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/354384.376408"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2008.09.007"},{"key":"ref22","first-page":"2944","article-title":"SUNDAy: Saliency using natural statistics for dynamic analysis of scenes","author":"zhang","year":"2009","journal-title":"Proc 4th Annu Conf Cogn Sci"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2008.4760948"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2259837"},{"key":"ref23","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2628583"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299189"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref51","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable mdps","author":"hausknecht","year":"2015","journal-title":"Proc Assoc Advance Artif Intell"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.30"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1037\/h0037368"},{"key":"ref54","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref52","first-page":"158","article-title":"Virtues of the haversine","volume":"68","author":"shumaker","year":"1984","journal-title":"Sky and Telescope"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.834657"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2496306"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.119"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2473844"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.343"},{"key":"ref16","first-page":"141","article-title":"Visualization and analysis of head movement and gaze data for immersive video in head-mounted displays","author":"l\u00f6we","year":"2015","journal-title":"Proc Workshop Eye Tracking Vis"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10708-007-9111-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.153"},{"key":"ref19","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2586304"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4097-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2016.2580913"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019351"},{"key":"ref8","first-page":"154","article-title":"Pano2vid: Automatic cinematography for watching 360-degree videos","author":"su","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.29"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025757"},{"key":"ref9","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Int Conf Mach Learn"},{"key":"ref46","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc 33rd Int Conf Int Conf Mach Learn"},{"key":"ref45","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.854388"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.871033"},{"key":"ref42","first-page":"3232","article-title":"Semantically-based human scanpath estimation with HMMs","author":"shao","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.275"},{"key":"ref44","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"0","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376414"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8855044\/08418756.pdf?arnumber=8418756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:09:04Z","timestamp":1657746544000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8418756\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,1]]},"references-count":57,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2018.2858783","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":[[2019,11,1]]}}}