{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T10:59:15Z","timestamp":1781607555450,"version":"3.54.5"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Zhejiang Natural Science Foundation","doi-asserted-by":"publisher","award":["LR19F020006"],"award-info":[{"award-number":["LR19F020006"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2018AAA0101400"],"award-info":[{"award-number":["2018AAA0101400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["61672409"],"award-info":[{"award-number":["61672409"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["61751209"],"award-info":[{"award-number":["61751209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["61836002"],"award-info":[{"award-number":["61836002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["61936006"],"award-info":[{"award-number":["61936006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Research Program of ZJU and Hikvision Research Institute and China Knowledge Center for Engineering Sciences"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2020.2985868","type":"journal-article","created":{"date-parts":[[2020,4,10]],"date-time":"2020-04-10T20:45:24Z","timestamp":1586551524000},"page":"5889-5899","source":"Crossref","is-referenced-by-count":60,"title":["Query-Biased Self-Attentive Network for Query-Focused Video Summarization"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2876-6601","authenticated-orcid":false,"given":"Shuwen","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-0384","authenticated-orcid":false,"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8308-768X","authenticated-orcid":false,"given":"Zijian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2413-4698","authenticated-orcid":false,"given":"Ziyu","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"216","article-title":"Video summarization via semantic attended networks","author":"wei","year":"2018","journal-title":"Proc 22nd AAAI Conf Artif Intell"},{"key":"ref38","article-title":"VideoSET: Video summary evaluation through text","author":"yeung","year":"2014","journal-title":"arXiv 1406 5824"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.112"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.120"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref30","first-page":"5179","article-title":"TVSum: Summarizing Web videos using titles","author":"song","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_12"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_32"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00776"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00773"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2320814"},{"key":"ref22","first-page":"361","article-title":"Video summarization using deep semantic features","author":"otani","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.322"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.538"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298981"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_19"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.395"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref54","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc 21st AAAI Conf Artif Intell"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1631144.1631154"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.496"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123297"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"ref13","first-page":"104","article-title":"Automatic video summarization by graph modeling","author":"ngo","year":"2003","journal-title":"Proc 9th IEEE Int Conf Comput Vis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.455"},{"key":"ref15","first-page":"7582","article-title":"Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward","author":"zhou","year":"2018","journal-title":"Proc 22nd AAAI Conf Artif Intell"},{"key":"ref16","first-page":"3618","article-title":"Video semantic clustering with sparse and incomplete tags","author":"wang","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.118"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.17"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601493"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.348"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.229"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.118"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_1"},{"key":"ref49","first-page":"5446","article-title":"Disan: Directional self-attention network for rnn\/cnn-free language understanding","author":"shen","year":"2018","journal-title":"Proc 22nd AAAI Conf Artif Intell"},{"key":"ref9","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"jae lee","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref45","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015","journal-title":"arXiv 1511 06732"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref41","article-title":"Query-conditioned three-player adversarial network for video summarization","author":"zhang","year":"2018","journal-title":"arXiv 1807 06677"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref43","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/09063637.pdf?arnumber=9063637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:12Z","timestamp":1651070352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9063637\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.2985868","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}