{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T19:26:46Z","timestamp":1779218806615,"version":"3.51.4"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2017YFB1300201"],"award-info":[{"award-number":["2017YFB1300201"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771457"],"award-info":[{"award-number":["61771457"]}],"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":["61732007"],"award-info":[{"award-number":["61732007"]}],"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":["61672497"],"award-info":[{"award-number":["61672497"]}],"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":["U19B2038"],"award-info":[{"award-number":["U19B2038"]}],"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":["61620106009"],"award-info":[{"award-number":["61620106009"]}],"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":["U1636214"],"award-info":[{"award-number":["U1636214"]}],"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":["61931008"],"award-info":[{"award-number":["61931008"]}],"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":["61772494"],"award-info":[{"award-number":["61772494"]}],"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":["62022083"],"award-info":[{"award-number":["62022083"]}],"id":[{"id":"10.13039\/501100001809","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":[[2022,2]]},"DOI":"10.1109\/tcsvt.2021.3063423","type":"journal-article","created":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T21:19:25Z","timestamp":1614719965000},"page":"880-892","source":"Crossref","is-referenced-by-count":76,"title":["Syntax-Guided Hierarchical Attention Network for Video Captioning"],"prefix":"10.1109","volume":"32","author":[{"given":"Jincan","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8437-4824","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beichen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5931-0527","authenticated-orcid":false,"given":"Shuhui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zhengjun","family":"Zha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref2","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref4","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc.,Comput. Linguistics, Hum. Lang. Technol.","volume":"1","author":"Chen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref6","first-page":"847","article-title":"Tvt: Two-view transformer network for video captioning","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Chen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123420"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00901"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351072"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"issue":"2","key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0531-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240667"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-42999-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2916167"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5201\/ipol.2013.26"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2921655"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984066"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.03.021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref40","article-title":"Translating videos to natural language using deep recurrent neural networks","volume-title":"arXiv:1412.4729","author":"Venugopalan","year":"2014"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2956593"},{"key":"ref45","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","volume-title":"arXiv:1609.08144","author":"Wu","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1213"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/548"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413885"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2936526"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9702151\/09367203.pdf?arnumber=9367203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:26:57Z","timestamp":1704842817000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9367203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2]]},"references-count":55,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2021.3063423","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2]]}}}