{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:46:52Z","timestamp":1772041612072,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP210102674"],"award-info":[{"award-number":["DP210102674"]}],"id":[{"id":"10.13039\/501100000923","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":[[2024,3]]},"DOI":"10.1109\/tcsvt.2023.3296196","type":"journal-article","created":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:55:22Z","timestamp":1689616522000},"page":"1469-1480","source":"Crossref","is-referenced-by-count":13,"title":["TLDW: Extreme Multimodal Summarization of News Videos"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3394-0114","authenticated-orcid":false,"given":"Peggy","family":"Tang","sequence":"first","affiliation":[{"name":"School of Computer Science, The University of Sydney, Camperdown, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6891-8059","authenticated-orcid":false,"given":"Kun","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney, Camperdown, NSW, Australia"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8043-0312","authenticated-orcid":false,"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney, Camperdown, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3117472"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531404"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.428"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486533"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2214871"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00901"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.inlg-1.23"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2904996"},{"key":"ref15","first-page":"967","article-title":"From word embeddings to document distances","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Kusner"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.460"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.752"},{"key":"ref18","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1387"},{"key":"ref21","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.648"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2009241"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3190998"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.108"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3044600"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1075\/nlp.3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462959"},{"key":"ref30","first-page":"404","article-title":"TextRank: Bringing order into text","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP)","author":"Mihalcea"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1206"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1158"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref34","article-title":"A deep reinforced model for abstractive summarization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Paulus"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206951"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.217"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093615"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-1099"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.229"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983349"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.newsum-1.15"},{"key":"ref43","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Cucurull"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350992"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2959451"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3197819"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2015.7371237"},{"key":"ref49","first-page":"11328","article-title":"PEGASUS: Pre-training with extracted gap-sentences for abstractive summarization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21422"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1499"},{"key":"ref52","first-page":"6634","article-title":"Multi-modal dependency tree for video captioning","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Zhao"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.552"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1448"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6525"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2940647"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10461325\/10185119.pdf?arnumber=10185119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T19:00:51Z","timestamp":1709924451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10185119\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":57,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3296196","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}