{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:38:04Z","timestamp":1775068684203,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"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":["U1736217"],"award-info":[{"award-number":["U1736217"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61932003"],"award-info":[{"award-number":["61932003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2019YFF0302902"],"award-info":[{"award-number":["2019YFF0302902"]}]},{"DOI":"10.13039\/501100011160","name":"State Key Laboratory of Virtual Reality Technology and Systems","doi-asserted-by":"publisher","award":["VRLAB2019C03"],"award-info":[{"award-number":["VRLAB2019C03"]}],"id":[{"id":"10.13039\/501100011160","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Defense Technology Innovation Program of China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/tmm.2019.2960656","type":"journal-article","created":{"date-parts":[[2019,12,18]],"date-time":"2019-12-18T20:53:22Z","timestamp":1576702402000},"page":"2623-2634","source":"Crossref","is-referenced-by-count":30,"title":["Deep Multimodality Learning for UAV Video Aesthetic Quality Assessment"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1675-1197","authenticated-orcid":false,"given":"Qi","family":"Kuang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3873-1653","authenticated-orcid":false,"given":"Xin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinping","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2091-1090","authenticated-orcid":false,"given":"Bin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964328"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532791"},{"key":"ref33","first-page":"77","article-title":"Predicting aesthetic score distribution through cumulative Jensen– Shannon divergence","author":"jin","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2018.5249"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.84"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2280250"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2189689"},{"key":"ref34","first-page":"386","article-title":"Photo and video quality evaluation: Focusing on the subject","author":"luo","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.119"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351067"},{"key":"ref29","first-page":"662","article-title":"Photo aesthetics ranking network with attributes and content adaptation","author":"kong","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3283254.3283260"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2479916"},{"key":"ref20","first-page":"419","article-title":"The design of high-level features for photo quality assessment","volume":"1","author":"ke","year":"0","journal-title":"Proc IEEE Comput Soc Conf Comput Vision Pattern Recognit"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995539"},{"key":"ref21","first-page":"288","article-title":"Studying aesthetics in photographic images using a computational approach","author":"datta","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126444"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995467"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654927"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2687759"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2013.6494384"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.04.005"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980409"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ITNG.2010.53"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2018.8484400"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0478-9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2907453"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.60"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.161"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref15","first-page":"978","article-title":"Multilayer and multimodal fusion of deep neural networks for video classification","author":"yang","year":"0","journal-title":"Proc ACM Multimedia Conf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477040"},{"key":"ref18","first-page":"198","article-title":"Classification of digital photos taken by photographers or home users","author":"tong","year":"0","journal-title":"Proc Pacific-Rim Conf Multimedia"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2303650"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2790163"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2911428"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30499-9_111"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641075"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2006.313037"},{"key":"ref7","first-page":"5398","article-title":"An SVM-based soccer video shot classification","volume":"9","author":"zhou","year":"0","journal-title":"Proc Int Conf Mach Learn Cybern"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854873"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2008.919173"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2237023"},{"key":"ref45","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","author":"qi","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit"},{"key":"ref48","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2658577"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2010.VI.010"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2777002"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9204776\/08936378.pdf?arnumber=8936378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:56:41Z","timestamp":1651075001000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8936378\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":56,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2960656","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}