{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T09:20:25Z","timestamp":1771233625602,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Program on Key Basic Research","award":["2015CB352300"],"award-info":[{"award-number":["2015CB352300"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1109\/tcsvt.2017.2771247","type":"journal-article","created":{"date-parts":[[2017,11,8]],"date-time":"2017-11-08T19:23:22Z","timestamp":1510169002000},"page":"226-237","source":"Crossref","is-referenced-by-count":67,"title":["Video Summarization by Learning Deep Side Semantic Embedding"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8701-7689","authenticated-orcid":false,"given":"Yitian","family":"Yuan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-7732","authenticated-orcid":false,"given":"Tao","family":"Mei","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2957-8511","authenticated-orcid":false,"given":"Peng","family":"Cui","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0494-3"},{"key":"ref38","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","first-page":"540","article-title":"Category-specific video summarization","author":"potapov","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1290082.1290114"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.12"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609568"},{"key":"ref37","first-page":"1558","article-title":"Unsupervised alignment of natural language instructions with video segments","author":"naim","year":"2014","journal-title":"Proc 28th AAAI Conf Artif Intell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.538"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.348"},{"key":"ref34","first-page":"787","article-title":"Ranking domain-specific highlights by analyzing edited videos","author":"sun","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref28","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2016.0081"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"907","DOI":"10.1109\/TMM.2005.854410","article-title":"A generic framework of user attention model and its application in video summarization","volume":"7","author":"ma","year":"2005","journal-title":"IEEE Trans Multimedia"},{"key":"ref1","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":"ref20","doi-asserted-by":"crossref","DOI":"10.1145\/2185520.2185564","article-title":"Videoscapes: Exploring sparse, unstructured video collections","volume":"31","author":"tompkin","year":"2012","journal-title":"ACM Trans Graph"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.120"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.111"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref23","first-page":"505","article-title":"Creating summaries from user videos","author":"gygli","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref26","first-page":"3","article-title":"Query-focused extractive video summarization","author":"sharghi","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref25","first-page":"766","article-title":"Video summarization with long short-term memory","author":"zhang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref51","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","author":"abadi","year":"2016","journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.08.004"},{"key":"ref11","first-page":"403","article-title":"Optimization algorithms for the selection of key frame sequences of variable length","author":"liu","year":"2002","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2651818"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.896640"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2012.10.002"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.514"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.112"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0794-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.31"},{"key":"ref4","first-page":"388","article-title":"Video summaries through mosaic-based shot and scene clustering","author":"aner","year":"2002","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.890857"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.179"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1998.698631"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.322"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2166951"},{"key":"ref49","first-page":"3294","article-title":"Skip-Thought vectors","author":"kiros","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.118"},{"key":"ref46","first-page":"1","article-title":"Sparse autoencoder","volume":"72","author":"ng","year":"2011","journal-title":"Cs294a lecture notes"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1961209.1961213"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101242"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502283"},{"key":"ref42","author":"kiros","year":"2014","journal-title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.483"},{"key":"ref44","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/8603859\/08101557.pdf?arnumber=8101557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:56:27Z","timestamp":1657745787000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8101557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":53,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2017.2771247","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1]]}}}