{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T18:41:39Z","timestamp":1780080099884,"version":"3.54.0"},"reference-count":62,"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":["61976057"],"award-info":[{"award-number":["61976057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572140"],"award-info":[{"award-number":["61572140"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Development Plan of Shanghai Science and Technology Commission","award":["20511101203"],"award-info":[{"award-number":["20511101203"]}]},{"name":"Science and Technology Development Plan of Shanghai Science and Technology Commission","award":["20511102702"],"award-info":[{"award-number":["20511102702"]}]},{"name":"Science and Technology Development Plan of Shanghai Science and Technology Commission","award":["20511101403"],"award-info":[{"award-number":["20511101403"]}]},{"name":"Science and Technology Development Plan of Shanghai Science and Technology Commission","award":["19DZ2205700"],"award-info":[{"award-number":["19DZ2205700"]}]},{"name":"Science and Technology Development Plan of Shanghai Science and Technology Commission","award":["2021SHZDZX0103"],"award-info":[{"award-number":["2021SHZDZX0103"]}]},{"DOI":"10.13039\/100007219","name":"Shanghai Natural Science Foundation","doi-asserted-by":"publisher","award":["19ZR1417200"],"award-info":[{"award-number":["19ZR1417200"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013139","name":"Humanities and Social Sciences Planning Fund of Ministry of Education of China","doi-asserted-by":"publisher","award":["19YJA630116"],"award-info":[{"award-number":["19YJA630116"]}],"id":[{"id":"10.13039\/501100013139","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":[[2022,1]]},"DOI":"10.1109\/tcsvt.2021.3058626","type":"journal-article","created":{"date-parts":[[2021,12,23]],"date-time":"2021-12-23T17:05:33Z","timestamp":1640279133000},"page":"31-42","source":"Crossref","is-referenced-by-count":41,"title":["Stacked Multimodal Attention Network for Context-Aware Video Captioning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5547-0956","authenticated-orcid":false,"given":"Yi","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7993-7223","authenticated-orcid":false,"given":"Yuejie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7561-0143","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1272-5538","authenticated-orcid":false,"given":"Weiguo","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. NIPS","author":"Sutskever"},{"key":"ref2","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. NIPS","author":"Krizhevsky"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref4","first-page":"2048","article-title":"Show, attend and tell: Neural image caption","volume-title":"Proc. ICML","author":"Xu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/496"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018271"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"issue":"2","key":"ref12","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1023\/A:1020346032608","article-title":"Natural language description of human activities from video images based on concept hierarchy of actions","volume":"50","author":"Kojima","year":"2002","journal-title":"Int. J. Comput. Vis."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123354"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/88"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/708"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/168"},{"key":"ref25","first-page":"656","article-title":"A neural compositional paradigm for image captioning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Dai"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240632"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Vaswani"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref34","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20133-319-10602-148"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref37","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref38","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"ref41","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Chen"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"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","author":"Banerjee"},{"key":"ref45","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1063\/1.4902458"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984065"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984066"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984062"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/164"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240667"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00042"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351060"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1213"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9678106\/09351972.pdf?arnumber=9351972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:17:34Z","timestamp":1704842254000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9351972\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":62,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2021.3058626","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1]]}}}