{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:18:26Z","timestamp":1791911906056,"version":"4.3.4"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Austrian-Chinese Cooperative Research and Development Project [Austrian Research Promotion Agency (FFG) and Chinese Academy of Sciences (CAS)]","doi-asserted-by":"publisher","award":["171111KYSB20200002"],"award-info":[{"award-number":["171111KYSB20200002"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association CAS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","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":[[2024,7]]},"DOI":"10.1109\/tcsvt.2023.3344097","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T20:04:55Z","timestamp":1702929895000},"page":"5977-5994","source":"Crossref","is-referenced-by-count":21,"title":["Momentum Cross-Modal Contrastive Learning for Video Moment Retrieval"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3763-5972","authenticated-orcid":false,"given":"De","family":"Han","sequence":"first","affiliation":[{"name":"Department of Institute of Computing Technology, Chinese Academy of Sciences, Haidian, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4942-4464","authenticated-orcid":false,"given":"Xing","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Institute of Computing Technology, Chinese Academy of Sciences, Haidian, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2250-5224","authenticated-orcid":false,"given":"Nan","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Institute of Computing Technology, Chinese Academy of Sciences, Haidian, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4598-1685","authenticated-orcid":false,"given":"Xiaochun","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Institute of Computing Technology, Chinese Academy of Sciences, Haidian, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1954-019X","authenticated-orcid":false,"given":"Benjamin","family":"Rainer","sequence":"additional","affiliation":[{"name":"Austrian Institute of Technology GmbH, Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7661-0604","authenticated-orcid":false,"given":"Peter","family":"Priller","sequence":"additional","affiliation":[{"name":"AVL List GmbH, Graz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"ref7","first-page":"1984","article-title":"Excl: Extractive clip localization using natural language descriptions","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol. (NAACL-HLTin)","volume":"1","author":"Ghosh"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3250518"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075470"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3272891"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3276979"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3283430"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3038993"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01137"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3120745"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413975"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1360\/SSI-2019-0292"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref31","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Kipf"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2021.3073867"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2022.3182866"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018175"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref41","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. 37th Int. Conf. Mach. Learn. (PMLR)","volume":"119","author":"Chen"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref43","first-page":"5171","article-title":"On variational bounds of mutual information","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","volume":"97","author":"Poole"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/2.36"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.04.023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIC57457.2023.10049967"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"ref57","article-title":"HuggingFace\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019","journal-title":"arXiv:1910.03771"},{"key":"ref58","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref59","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref62","article-title":"Tripping through time: Efficient localization of activities in videos","volume-title":"Proc. 31st Brit. Mach. Vis. Conf. (BMVC)","author":"Hahn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44693-1_34"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00258"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3174136"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3090521"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3179314"},{"key":"ref69","article-title":"Uncovering hidden challenges in query-based video moment retrieval","volume-title":"Proc. 31st Brit. Mach. Vis. Conf. (BMVC)","author":"Otani"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10582818\/10364740.pdf?arnumber=10364740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T04:00:32Z","timestamp":1720152032000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10364740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":70,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3344097","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}