{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T12:01:55Z","timestamp":1774699315353,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1109\/tcsvt.2022.3183648","type":"journal-article","created":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T19:35:40Z","timestamp":1655408140000},"page":"8051-8064","source":"Crossref","is-referenced-by-count":9,"title":["SentiStory: A Multi-Layered Sentiment-Aware Generative Model for Visual Storytelling"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2035-9737","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2705-8731","authenticated-orcid":false,"given":"Xuefeng","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3946-5107","authenticated-orcid":false,"given":"Jianwei","family":"Niu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3036860"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16249"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref6","article-title":"GLAC Net: GLocal attention cascading networks for multi-image cued story generation","author":"Kim","year":"2018","journal-title":"arXiv:1805.10973"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/744"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1083"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018465"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6305"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3123818.3123852"},{"key":"ref12","volume-title":"Poor Old Mum!","author":"Hunt","year":"1992"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-558701-3.50007-7"},{"key":"ref14","article-title":"DeepSentiBank: Visual sentiment concept classification with deep convolutional neural networks","author":"Chen","year":"2014","journal-title":"arXiv:1410.8586"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806246"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00636"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01034"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01094"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref23","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref24","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref25","first-page":"1","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Herdade"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1101"},{"key":"ref29","article-title":"Contextualize, show and tell: A neural visual storyteller","author":"Gonzalez-Rico","year":"2018","journal-title":"arXiv:1806.00738"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018909"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1658"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350918"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.conll-1.34"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16184"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10760"},{"key":"ref36","first-page":"3679","article-title":"Representing general relational knowledge in ConceptNet 5","volume-title":"Proc. LREC","author":"Speer"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1409360.1409378"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1098"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6303"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12318"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325050"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref44","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref45","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9931687\/09797749.pdf?arnumber=9797749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:44:24Z","timestamp":1706762664000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9797749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":46,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3183648","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11]]}}}