{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:16:30Z","timestamp":1753600590660,"version":"3.37.3"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976159","52102382"],"award-info":[{"award-number":["61976159","52102382"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Innovation Action Project of Science and Technology","award":["20511100700"],"award-info":[{"award-number":["20511100700"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/tcsvt.2022.3199603","type":"journal-article","created":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T19:40:33Z","timestamp":1660765233000},"page":"257-268","source":"Crossref","is-referenced-by-count":6,"title":["Coherent Visual Storytelling via Parallel Top-Down Visual and Topic Attention"],"prefix":"10.1109","volume":"33","author":[{"given":"Jinjing","family":"Gu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-4871","authenticated-orcid":false,"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruichao","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/137"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecresq.2019.12.009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3058688"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075470"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1083"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018465"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6305"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.204"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3020877"},{"key":"ref11","article-title":"Contextualize, show and tell: A neural visual storyteller","author":"Gonzalez-Rico","year":"2018","journal-title":"arxiv:1805.00738"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018909"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33894-7_30"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930041"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6780"},{"key":"ref16","first-page":"12747","article-title":"Two heads are better than one: Hypergraph-enhanced graph reasoning for visual event ratiocination","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","author":"Zheng"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16410"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00676"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3183648"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01247"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.390"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413886"},{"key":"ref23","article-title":"GLAC Net: GLocal attention cascading networks for multi-image cued story generation","author":"Kim","year":"2018","journal-title":"arXiv:1805.10973"},{"key":"ref24","first-page":"1","article-title":"Proceedings of the first workshop on storytelling","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics (ACL)","author":"Mitchell"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.364"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/132"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1013"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2997034"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/592"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060713"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-017-1004-2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126715"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/744"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350918"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063423"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2017.8053242"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0307752101"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6333"},{"key":"ref48","article-title":"Mutual information and diverse decoding improve neural machine translation","author":"Li","year":"2016","journal-title":"arXiv:1601.00372"},{"key":"ref49","article-title":"Diverse beam search: Decoding diverse solutions from neural sequence models","author":"Vijayakumar","year":"2016","journal-title":"arXiv:1610.02424"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref53","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. 45th Annu. Meeting Assoc. Comput. Linguistics (ACL)","author":"Banerjee"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3355390"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1101"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6455"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16184"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1002\/pra2.374"},{"key":"ref59","first-page":"100","article-title":"Automatic evaluation of topic coherence","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics (NAACL)","author":"Newman"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/E14-1056"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10007626\/09858883.pdf?arnumber=9858883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:12:53Z","timestamp":1706789573000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9858883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":60,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3199603","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}