{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,8]],"date-time":"2025-03-08T05:29:57Z","timestamp":1741411797303,"version":"3.38.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["62206137"],"award-info":[{"award-number":["62206137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin Municipality","doi-asserted-by":"publisher","award":["22JCQNJC00940"],"award-info":[{"award-number":["22JCQNJC00940"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013147","name":"Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region","doi-asserted-by":"publisher","award":["NJYT23105"],"award-info":[{"award-number":["NJYT23105"]}],"id":[{"id":"10.13039\/501100013147","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":[[2025,3]]},"DOI":"10.1109\/tcsvt.2024.3498599","type":"journal-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T18:43:24Z","timestamp":1731609804000},"page":"2894-2904","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Diversify for Robust Video Moment Retrieval"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9175-5668","authenticated-orcid":false,"given":"Huilin","family":"Ge","sequence":"first","affiliation":[{"name":"College of Ocean, Jiangsu University of Science and Technology, Zhenjiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2671-5709","authenticated-orcid":false,"given":"Xiaolei","family":"Liu","sequence":"additional","affiliation":[{"name":"Elevoc Technology Company Ltd., Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8357-2254","authenticated-orcid":false,"given":"Zihang","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5112-1757","authenticated-orcid":false,"given":"Zhiwen","family":"Qiu","sequence":"additional","affiliation":[{"name":"College of Ocean, Jiangsu University of Science and Technology, Zhenjiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2940647"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3362270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3298937"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002669"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016391"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01514-3"},{"key":"ref10","article-title":"DualVGR: A dual-visual graph reasoning unit for video question answering","author":"Wang","year":"2021","journal-title":"arXiv:2107.04768"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248873"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239183"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.327"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref21","first-page":"1984","article-title":"EXCL: Extractive clip localization using natural language descriptions","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Ghosh"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018175"},{"key":"ref23","article-title":"End-to-end multi-modal video temporal grounding","author":"Chen","year":"2021","journal-title":"arXiv:2107.05624"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531403"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.324"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/143"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3344097"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00112"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16285"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3783-3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3389024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00365"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00834"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref44","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"volume-title":"spacy: Industrial-strength natural language processing in Python","year":"2020","author":"Matthew","key":"ref46"},{"key":"ref47","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref50","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","volume":"27","author":"Simonyan"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"ref54","first-page":"534","article-title":"Semantic conditioned dynamic modulation for temporal sentence grounding in videos","volume-title":"Proc. NeurIPS","author":"Yuan"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10916540\/10753081.pdf?arnumber=10753081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:50:53Z","timestamp":1741373453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10753081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":55,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3498599","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}