{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T23:17:08Z","timestamp":1776122228816,"version":"3.50.1"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"CloudWalk Technology Company Ltd."},{"name":"Key Research and Development Program of Chongqing","award":["cstc2021jscx-gksbX0032"],"award-info":[{"award-number":["cstc2021jscx-gksbX0032"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3250518","type":"journal-article","created":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T18:54:48Z","timestamp":1677610488000},"page":"5281-5295","source":"Crossref","is-referenced-by-count":44,"title":["Video Moment Retrieval via Comprehensive Relation-Aware Network"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3092-0583","authenticated-orcid":false,"given":"Xin","family":"Sun","sequence":"first","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8554-7827","authenticated-orcid":false,"given":"Jialin","family":"Gao","sequence":"additional","affiliation":[{"name":"AI Singapore, National University of Singapore, Queenstown, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3686-4420","authenticated-orcid":false,"given":"Yizhe","family":"Zhu","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4456-0603","authenticated-orcid":false,"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Guanghua School of Management, Peking University, Beijing, China"}]},{"given":"Xi","family":"Zhou","sequence":"additional","affiliation":[{"name":"CloudWalk Technology Company Ltd., Shanghai, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref57","article-title":"SaGCN: Semantic-aware graph calibration network for temporal sentence grounding","author":"chen","year":"2022","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00361"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.324"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2962063"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018303"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428369"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2965987"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2957854"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3120745"},{"key":"ref18","first-page":"2725","article-title":"Semantic conditioned dynamic modulation for temporal sentence grounding in videos","volume":"44","author":"yuan","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2985708"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113791"},{"key":"ref46","first-page":"1693","article-title":"Teaching machines to read and comprehend","volume":"28","author":"hermann","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413840"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142420"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1082"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3086591"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3090521"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413841"},{"key":"ref85","first-page":"4252","article-title":"Natural language video localization: A revisit in span-based question answering framework","volume":"44","author":"zhang","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531394"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3052086"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014491"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048440"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2473295"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3051277"},{"key":"ref82","first-page":"510","article-title":"Hollywood in homes: Crowdsourcing data collection for activity understanding","author":"sigurdsson","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414026"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3023339"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01091"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413975"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063631"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16285"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_28"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref77","first-page":"1","article-title":"Bidirectional attention flow for machine comprehension","author":"seo","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"ref76","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref39","article-title":"Tripping through time: Efficient localization of activities in videos","author":"hahn","year":"2019","journal-title":"arXiv 1904 09936"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174136"},{"key":"ref71","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.733"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532083"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00695"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3168424"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075470"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073867"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120038"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref28","first-page":"1984","article-title":"ExCL: Extractive clip localization using natural language descriptions","volume":"1","author":"ghosh","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414053"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075607"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096087"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2953187"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10056330.pdf?arnumber=10056330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:41:19Z","timestamp":1695667279000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10056330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":90,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3250518","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}