{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:02:03Z","timestamp":1776182523404,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["U20B2063"],"award-info":[{"award-number":["U20B2063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program, China","award":["2020YFS0057"],"award-info":[{"award-number":["2020YFS0057"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Dongguan Songshan Lake Introduction Program of Leading Innovative and Entrepreneurial Talents"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1109\/tcsvt.2021.3063297","type":"journal-article","created":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T21:19:25Z","timestamp":1614719965000},"page":"52-62","source":"Crossref","is-referenced-by-count":36,"title":["Entity Slot Filling for Visual Captioning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9714-8738","authenticated-orcid":false,"given":"Yi","family":"Bin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2945-1107","authenticated-orcid":false,"given":"Yujuan","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6616-453X","authenticated-orcid":false,"given":"Bo","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0576-1429","authenticated-orcid":false,"given":"Liang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855415"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00640"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref36","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6389-3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00433"},{"key":"ref60","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"Proc ECCV"},{"key":"ref61","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.364"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_45"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref2","article-title":"Exploiting subspace relation in semantic labels for cross-modal hashing","author":"shen","year":"2020","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref20","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"2011","journal-title":"Proc EMNLP"},{"key":"ref22","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref21","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc ICML"},{"key":"ref24","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855422"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123391"},{"key":"ref50","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref58","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"2004","journal-title":"Proc ACL"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"ref54","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref10","article-title":"Text infilling","author":"zhu","year":"2019","journal-title":"arXiv 1901 00158"},{"key":"ref11","first-page":"1","article-title":"MaskGAN: Better text generation via filling in the_","author":"fedus","year":"2018","journal-title":"Proc ICLR"},{"key":"ref40","first-page":"1564","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1055"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.778"},{"key":"ref15","article-title":"Video fill in the blank with merging LSTMs","author":"mazaheri","year":"2016","journal-title":"arXiv 1610 04062"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref18","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"Proc ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"ref6","first-page":"1112","article-title":"Hierarchical LSTMs with adaptive attention for visual captioning","volume":"42","author":"gao","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004830"},{"key":"ref46","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref45","first-page":"121","article-title":"OSCAR: Object-semantics aligned pre-training for vision-language tasks","author":"li","year":"2020","journal-title":"Proc ECCV"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.763"},{"key":"ref41","first-page":"856","article-title":"Bidirectional recurrent neural networks as generative models","author":"berglund","year":"2015","journal-title":"Proc NeurIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1406"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9678106\/09366817.pdf?arnumber=9366817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T17:55:47Z","timestamp":1649440547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9366817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":61,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2021.3063297","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1]]}}}