{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:21:16Z","timestamp":1775578876372,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Fund for Distinguished Young Scholars of China","award":["61725105"],"award-info":[{"award-number":["61725105"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3157993","type":"journal-article","created":{"date-parts":[[2022,3,9]],"date-time":"2022-03-09T20:26:08Z","timestamp":1646857568000},"page":"3296-3310","source":"Crossref","is-referenced-by-count":10,"title":["Abstractive Summarization for Video: A Revisit in Multistage Fusion Network With Forget Gate"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7664-9856","authenticated-orcid":false,"given":"Nayu","family":"Liu","sequence":"first","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0038-9816","authenticated-orcid":false,"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Hongfeng","family":"Yu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4187-9755","authenticated-orcid":false,"given":"Fanglong","family":"Yao","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3529-593X","authenticated-orcid":false,"given":"Guangluan","family":"Xu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0450-6469","authenticated-orcid":false,"given":"Kun","family":"Fu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"How2: A large-scale dataset for multimodal language understanding","author":"sanabria","year":"0","journal-title":"Proc Workshop Int Conf Neural Inf Process Syst"},{"key":"ref12","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.144"},{"key":"ref14","article-title":"Google's speech to text API (v2)","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlpbt-1.7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1659"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1114"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2267205"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.05.022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2809932"},{"key":"ref46","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.072"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref47","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref41","first-page":"74","article-title":"ROUGE: A. package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref44","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref8","first-page":"11?328","article-title":"PEGASUS: Pre-training with extracted gap-sentences for abstractive summarization","author":"zhang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1387"},{"key":"ref9","first-page":"1","article-title":"Multimodal abstractive summarization of open-domain videos","author":"libovick?","year":"0","journal-title":"Proc Workshop Int Conf Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2987683"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1158"},{"key":"ref6","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3021980"},{"key":"ref40","first-page":"1","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref35","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6525"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1448"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2031"},{"key":"ref38","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2822907"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2384912"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/577"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1008"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-3689-7_6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505652"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2997020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1438"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2624140"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09732216.pdf?arnumber=9732216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:02:22Z","timestamp":1693245742000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9732216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3157993","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}