{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:28:57Z","timestamp":1780511337946,"version":"3.54.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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":[{"name":"National Key R&D Program of China","award":["2022YFF1202903"],"award-info":[{"award-number":["2022YFF1202903"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972188"],"award-info":[{"award-number":["61972188"]}],"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":["62122035"],"award-info":[{"award-number":["62122035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3232022","type":"journal-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:16:59Z","timestamp":1672082219000},"page":"7894-7905","source":"Crossref","is-referenced-by-count":5,"title":["Show, Tell and Rephrase: Diverse Video Captioning via Two-Stage Progressive Training"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3737-2161","authenticated-orcid":false,"given":"Zhu","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2331-3619","authenticated-orcid":false,"given":"Teng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5531-4160","authenticated-orcid":false,"given":"Jinrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1701-9141","authenticated-orcid":false,"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0795-366X","authenticated-orcid":false,"given":"Wenhao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Data Platform, Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0176-3088","authenticated-orcid":false,"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of C hinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002669"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref11","first-page":"2454","article-title":"Learn from your neighbor: Learning multi-modal mappings from sparse annotations","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Kalyan","year":"2018"},{"key":"ref12","first-page":"3613","article-title":"Diverse image captioning with context-object split latent spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Mahajan","year":"2020,"},{"key":"ref13","first-page":"1929","article-title":"Variational structured semantic inference for diverse image captioning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Chen","year":"2019,"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00436"},{"key":"ref15","first-page":"5756","article-title":"Diverse and accurate image description using a variational auto-encoder with an additive Gaussian encoding space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00434"},{"key":"ref17","first-page":"1","article-title":"Understanding posterior collapse in generative latent variable models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lucas","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1002"},{"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":"10.24963\/ijcai.2020\/104"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123420"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/88"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3003592"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref30","first-page":"1","article-title":"A better use of audio-visual cues: Dense video captioning with bi-modal transformer","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Iashin","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01657"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00255"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref40","first-page":"1","article-title":"Latent normalizing flows for many-to-many cross-domain mappings","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mahajan","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref43","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2015"},{"key":"ref44","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. Assoc. Comput. Linguistics","author":"Chen","year":"2011"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref46","article-title":"Clip2video: Mastering video-text retrieval via image clip","author":"Fang","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00432"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref51","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3355390"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09999037.pdf?arnumber=9999037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T23:45:29Z","timestamp":1703029529000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9999037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3232022","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}