{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T01:31:53Z","timestamp":1768095113839,"version":"3.49.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"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":["2022YFC2009903"],"award-info":[{"award-number":["2022YFC2009903"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFC2009900"],"award-info":[{"award-number":["2022YFC2009900"]}],"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":["62122018"],"award-info":[{"award-number":["62122018"]}],"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":["62020106008"],"award-info":[{"award-number":["62020106008"]}],"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":["61772116"],"award-info":[{"award-number":["61772116"]}],"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":["61872064"],"award-info":[{"award-number":["61872064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004806","name":"Fok Ying Tong Education Foundation","doi-asserted-by":"publisher","award":["171106"],"award-info":[{"award-number":["171106"]}],"id":[{"id":"10.13039\/501100004806","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Songshan Laboratory","award":["YYJC012022019"],"award-info":[{"award-number":["YYJC012022019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tcsvt.2023.3235523","type":"journal-article","created":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T21:23:27Z","timestamp":1673299407000},"page":"4362-4374","source":"Crossref","is-referenced-by-count":23,"title":["Complementarity-Aware Space Learning for Video-Text Retrieval"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7360-7119","authenticated-orcid":false,"given":"Jinkuan","family":"Zhu","sequence":"first","affiliation":[{"name":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0672-3790","authenticated-orcid":false,"given":"Pengpeng","family":"Zeng","sequence":"additional","affiliation":[{"name":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gongfu","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongliang","family":"Liao","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref14","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350906"},{"key":"ref11","first-page":"1","article-title":"Use what you have: Video retrieval using representations from collaborative experts","author":"liu","year":"2019","journal-title":"Proc BMVC"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref17","article-title":"Temporal multi-modal graph transformer with global-local alignment for video-text retrieval","author":"feng","year":"2022","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462974"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401151"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01638"},{"key":"ref45","article-title":"GODIVA: Generating open-DomaIn videos from nAtural descriptions","author":"wu","year":"2021","journal-title":"arXiv 2104 14806"},{"key":"ref48","first-page":"487","article-title":"A joint sequence fusion model for video question answering and retrieval","volume":"11211","author":"yu","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/307"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref49","article-title":"Learning a text-video embedding from incomplete and heterogeneous data","author":"miech","year":"2018","journal-title":"arXiv 1804 02516"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref7","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Proc BMVC"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475380"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01086"},{"key":"ref6","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127905"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3058626"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/224"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351072"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205212"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref39","first-page":"613","article-title":"Generating videos with scene dynamics","volume":"29","author":"vondrick","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"1","article-title":"Support-set bottlenecks for video-text representation learning","author":"patrick","year":"2021","journal-title":"Proc ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3017344"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037661"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011288"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475515"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10207864\/10012341.pdf?arnumber=10012341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T18:10:59Z","timestamp":1692641459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10012341\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":54,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3235523","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}