{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T15:44:27Z","timestamp":1765295067619,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"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 Future Fellowship","doi-asserted-by":"publisher","award":["FT180100116"],"award-info":[{"award-number":["FT180100116"]}],"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":[[2020,9]]},"DOI":"10.1109\/tcsvt.2019.2936526","type":"journal-article","created":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T19:46:57Z","timestamp":1566503217000},"page":"3130-3139","source":"Crossref","is-referenced-by-count":35,"title":["Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8867-3888","authenticated-orcid":false,"given":"Zhiwang","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2775-9730","authenticated-orcid":false,"given":"Dong","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9163-2761","authenticated-orcid":false,"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1197-4807","authenticated-orcid":false,"given":"Chuanqi","family":"Tan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref33","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2014","journal-title":"Arxiv 1412 7755"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref36","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00714"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00834"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01229"},{"key":"ref18","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"venugopalan","year":"2014","journal-title":"arXiv 1412 4729"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1523"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459279"},{"key":"ref29","first-page":"4263","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","volume":"1","author":"song","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref22","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref42","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967298"},{"key":"ref43","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"2004","journal-title":"Proc ACL Workshop Text Summarization Branches Out"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806314"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9185141\/08807239.pdf?arnumber=8807239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:52Z","timestamp":1651070392000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8807239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9]]},"references-count":45,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2019.2936526","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2020,9]]}}}