{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:20:03Z","timestamp":1775578803247,"version":"3.50.1"},"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":"National Key Research and Development Program of China","award":["2018YFB1004300"],"award-info":[{"award-number":["2018YFB1004300"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3037461","type":"journal-article","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T21:04:41Z","timestamp":1605128681000},"page":"4027-4036","source":"Crossref","is-referenced-by-count":9,"title":["Story-driven Video Editing"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6753-6569","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"first","affiliation":[]},{"given":"Jianguo","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","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"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240535"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.340"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.640"},{"key":"ref30","article-title":"Show, control and tell: A framework for generating controllable and grounded captions","author":"cornia","year":"2018","journal-title":"arXiv 1811 10652"},{"key":"ref37","first-page":"374","article-title":"Cross-modal and hierarchical modeling of video and text","author":"zhang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref36","article-title":"Grounded video description","author":"zhou","year":"2018","journal-title":"arXiv 1812 06587"},{"key":"ref35","article-title":"Learning a text-video embedding from incomplete and heterogeneous data","author":"miech","year":"2018","journal-title":"arXiv 1804 02516"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00772"},{"key":"ref28","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref27","first-page":"2692","article-title":"Pointer networks","author":"vinyals","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref29","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"bai","year":"2018","journal-title":"arXiv 1803 01271"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886275"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.827505"},{"key":"ref20","first-page":"2025","article-title":"Unsupervised alignment of actions in video with text descriptions","author":"song","year":"0","journal-title":"Int Joint Conf Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325047"},{"key":"ref21","first-page":"1993","article-title":"Ranking and retrieval of image sequences from multiple paragraph queries","author":"kim","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356520"},{"key":"ref23","article-title":"TRECVID 2018: Benchmarking video activity detection, video captioning and matching, video storytelling linking and video search","author":"awad","year":"2018","journal-title":"Proc TRECVID"},{"key":"ref26","article-title":"Sentence ordering using recurrent neural networks","author":"logeswaran","year":"2016"},{"key":"ref25","article-title":"Order matters: Sequence to sequence for sets","author":"vinyals","year":"2015","journal-title":"arXiv 1511 06391"},{"key":"ref50","article-title":"In defense of the triplet loss for person re-identification","author":"hermans","year":"2017","journal-title":"arXiv 1703 07737"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref55","article-title":"Learning latent permutations with gumbel-sinkhorn networks","author":"mena","year":"2018","journal-title":"arXiv 1802 08665"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/BF01588971"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281239"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2002.802022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.921735"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127906"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1178677.1178709"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2229972"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-014-0065-9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2508146"},{"key":"ref6","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"venugopalan","year":"2014","journal-title":"arXiv 1412 4729"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532983"},{"key":"ref8","article-title":"Tunneling neural perception and logic reasoning through abductive learning","author":"dai","year":"2018","journal-title":"arXiv 1802 01173"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240583"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref47","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Assoc Adv Artif Intell"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref44","first-page":"1571","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09257101.pdf?arnumber=9257101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:29Z","timestamp":1652194289000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9257101\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3037461","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}