{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:28:25Z","timestamp":1783736905189,"version":"3.55.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"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":["62176139"],"award-info":[{"award-number":["62176139"]}],"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":["62106128"],"award-info":[{"award-number":["62106128"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Basic Research Project of Shandong Natural Science Foundation","award":["ZR2021ZD15"],"award-info":[{"award-number":["ZR2021ZD15"]}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2021QF001"],"award-info":[{"award-number":["ZR2021QF001"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientists Sponsorship Program by the China Association for Science and Technology","award":["2021QNRC001"],"award-info":[{"award-number":["2021QNRC001"]}]},{"name":"Open Project of Key Laboratory of Artificial Intelligence, Ministry of Education, through the Shandong Provincial Natural Science Foundation for Distinguished Young Scholars","award":["ZR2021JQ26"],"award-info":[{"award-number":["ZR2021JQ26"]}]},{"name":"Open Research Project Programme of the State Key Laboratory of Internet of Things for Smart City","award":["SKL-IoTSC(UM)-2021-2023\/ORP\/GA05\/2022"],"award-info":[{"award-number":["SKL-IoTSC(UM)-2021-2023\/ORP\/GA05\/2022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tcsvt.2023.3294567","type":"journal-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T17:25:45Z","timestamp":1689182745000},"page":"6686-6698","source":"Crossref","is-referenced-by-count":15,"title":["Video Corpus Moment Retrieval via Deformable Multigranularity Feature Fusion and Adversarial Training"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8422-0929","authenticated-orcid":false,"given":"Xuemei","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2666-0299","authenticated-orcid":false,"given":"Peng","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5360-919X","authenticated-orcid":false,"given":"Jinsheng","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9543-6960","authenticated-orcid":false,"given":"Xiankai","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8465-1294","authenticated-orcid":false,"given":"Yilong","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref3","article-title":"A hierarchical multi-modal encoder for moment localization in video corpus","author":"Zhang","year":"2020","journal-title":"arXiv:2011.09046"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"ref5","article-title":"Temporal localization of moments in video collections with natural language","author":"Escorcia","year":"2019","journal-title":"arXiv:1907.12763"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413840"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3169\/mta.4.187"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1168"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414053"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207265"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00852"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225573"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00223"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475281"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3156367"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547976"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123456"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475342"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16760"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3272826"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3052086"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref39","article-title":"EXCL: Extractive clip localization using natural language descriptions","author":"Ghosh","year":"2019","journal-title":"arXiv:1904.02755"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3060449"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3258628"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1157"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.324"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075470"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475515"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2932666"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220012"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2932742"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3080293"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298641"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127492"},{"key":"ref63","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref65","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref67","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017","journal-title":"arXiv:1706.06083"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.5220\/0007370301640173"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134057"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.01442"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3161905"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00191"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00078"},{"key":"ref74","first-page":"11278","article-title":"Attacks which do not kill training make adversarial learning stronger","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00206"},{"key":"ref76","first-page":"16199","article-title":"Robust pre-training by adversarial contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Jiang"},{"key":"ref77","first-page":"2983","article-title":"Adversarial self-supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kim"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref82","first-page":"1","article-title":"Bidirectional attention flow for machine comprehension","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Seo"},{"key":"ref83","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Gutmann"},{"key":"ref84","article-title":"Exploring the limits of language modeling","author":"Jozefowicz","year":"2016","journal-title":"arXiv:1602.02410"},{"key":"ref85","article-title":"Learning video representations using contrastive bidirectional transformer","author":"Sun","year":"2019","journal-title":"arXiv:1906.05743"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref87","first-page":"1","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hjelm"},{"key":"ref88","first-page":"1","article-title":"Deep graph infomax","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Velickovic"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_11"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10179965.pdf?arnumber=10179965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:50:56Z","timestamp":1723528256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10179965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":89,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3294567","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}