{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T03:15:07Z","timestamp":1784776507742,"version":"3.55.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"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":["61472273"],"award-info":[{"award-number":["61472273"]}],"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":["61632018"],"award-info":[{"award-number":["61632018"]}],"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":["61771329"],"award-info":[{"award-number":["61771329"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004356","name":"Nokia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004356","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/tcsvt.2019.2904996","type":"journal-article","created":{"date-parts":[[2019,3,14]],"date-time":"2019-03-14T18:55:42Z","timestamp":1552589742000},"page":"1709-1717","source":"Crossref","is-referenced-by-count":301,"title":["Video Summarization With Attention-Based Encoder\u2013Decoder Networks"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2197-3739","authenticated-orcid":false,"given":"Zhong","family":"Ji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kailin","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1556215"},{"key":"ref33","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_5"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.09.050"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2166951"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2493558"},{"key":"ref36","year":"2016","journal-title":"Open Video Project"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2513678"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2557785"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2013.08.003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.08.004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.08.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2007.04.002"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1198302.1198305"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref21","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.526"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2012.10.002"},{"key":"ref25","first-page":"5179","article-title":"TVSum: Summarizing web videos using titles","author":"song","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2601438"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-017-9158-x"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.841694"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2005.856896"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052025"},{"key":"ref12","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"lee","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.348"},{"key":"ref14","first-page":"2069","article-title":"Diverse sequential subset selection for supervised video summarization","author":"gong","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"3652","DOI":"10.1109\/TIP.2017.2695887","article-title":"A general framework for edited video and raw video summarization","volume":"26","author":"xuelong","year":"2017","journal-title":"IEEE Trans Image Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2185041"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2532719"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2539638"},{"key":"ref8","first-page":"1618","article-title":"Pairwise relationship guided deep hashing for cross-modal retrieval","volume":"2017","author":"yang","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2710635"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9497-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.09.063"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_32"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2694224"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_24"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00773"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.120"},{"key":"ref44","first-page":"1410","article-title":"A memory network approach for story-based temporal summarization of 360° videos","author":"sangho","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_10"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9108324\/08667390.pdf?arnumber=8667390","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:46Z","timestamp":1651070386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8667390\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":51,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2019.2904996","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}