{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T10:10:14Z","timestamp":1776852614310,"version":"3.51.2"},"reference-count":57,"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":[{"name":"NSFC Projects","award":["61876013"],"award-info":[{"award-number":["61876013"]}]},{"name":"NSFC Projects","award":["61922009"],"award-info":[{"award-number":["61922009"]}]},{"name":"NSFC Projects","award":["61573037"],"award-info":[{"award-number":["61573037"]}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ20019"],"award-info":[{"award-number":["JQ20019"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3021984","type":"journal-article","created":{"date-parts":[[2020,9,4]],"date-time":"2020-09-04T20:55:45Z","timestamp":1599252945000},"page":"3227-3238","source":"Crossref","is-referenced-by-count":11,"title":["Attention-Based Deep Reinforcement Learning for Virtual Cinematography of 360$^{\\circ}$ Videos"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7025-3626","authenticated-orcid":false,"given":"Jianyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0277-3301","authenticated-orcid":false,"given":"Mai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lai","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"xingjian","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/543"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2845370"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754941"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.343"},{"key":"ref30","first-page":"1","article-title":"SalGAN: Visual saliency prediction with generative adversarial networks","author":"pan","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit Workshop"},{"key":"ref37","first-page":"274","article-title":"An integrated model for effective saliency prediction","author":"sun","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777665"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2169775"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2851389"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_50"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref29","first-page":"1","article-title":"Recurrent mixture density network for spatiotemporal visual attention","author":"bazzani","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858783"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/354384.376408"},{"key":"ref20","first-page":"428","article-title":"Human detection using oriented histograms of flow and appearance","author":"dalal","year":"2006","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2259837"},{"key":"ref21","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":"Appl and Sci of Neural Networks Fuzzy Systems and Evolutionary Comput VI"},{"key":"ref24","first-page":"1063","article-title":"Video saliency detection via dynamic consistent spatio-temporal attention modelling","author":"zhong","year":"2013","journal-title":"Proc 27th AAAI Conf Artif Intell"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502128"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.358"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025223"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1167\/11.5.13"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1179\/sre.1975.23.176.88"},{"key":"ref57","article-title":"Saliency detection in 360 videos","author":"zhang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2018.8551523"},{"key":"ref55","author":"snyder","year":"1997","journal-title":"Flattening the earth Two thousand years of map projections"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref52","first-page":"536","article-title":"On the theory of filter amplifiers","volume":"7","author":"butterworth","year":"1930","journal-title":"Wireless Eng"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"ref11","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.05.010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237259"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21236\/ADA464770"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.854388"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.871033"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2788539.2788549"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2015.36"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.507"},{"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 Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.153"},{"key":"ref3","first-page":"1368","article-title":"Making 360 video watchable in 2\ufffdd: Learning videography for click free viewing","author":"su","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref6","article-title":"A deep ranking model for spatio-temporal highlight detection from a $360^{\\circ}$ video","author":"yu","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref5","first-page":"154","article-title":"Pano2vid: Automatic cinematography for watching $360^{\\circ}$ videos","author":"su","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-720"},{"key":"ref7","first-page":"1410","article-title":"A memory network approach for story-based temporal summarization of $360^{\\circ}$ videos","author":"lee","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/nature14540"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240669"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.03.006"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3083165.3083180"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_30"},{"key":"ref42","first-page":"1420","article-title":"Cube padding for weakly-supervised saliency prediction in $360^{\\circ}$ videos","author":"cheng","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.05.005"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.03.007"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00358"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09186833.pdf?arnumber=9186833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:19Z","timestamp":1652194279000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9186833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3021984","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}