{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T05:06:15Z","timestamp":1741323975283,"version":"3.38.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Planning and Evaluation (IITP), Korean Government [Ministry of Science and ICT (MSIT)]","doi-asserted-by":"publisher","award":["RS-2022-II220077","RS-2022-II220113","RS-2022-II220959","RS-2020-II201361"],"award-info":[{"award-number":["RS-2022-II220077","RS-2022-II220113","RS-2022-II220959","RS-2020-II201361"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"[Yonsei Artificial Intelligence (AI)]","award":["RS-2021-II211343"],"award-info":[{"award-number":["RS-2021-II211343"]}]},{"DOI":"10.13039\/501100002551","name":"[Seoul National University (SNU) AI]","doi-asserted-by":"publisher","award":["RS-2021-II212068"],"award-info":[{"award-number":["RS-2021-II212068"]}],"id":[{"id":"10.13039\/501100002551","id-type":"DOI","asserted-by":"publisher"}]},{"name":"(AI Innovation Hub)"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3542720","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T18:41:32Z","timestamp":1740422492000},"page":"38574-38583","source":"Crossref","is-referenced-by-count":0,"title":["Moment-Aware Video Retrieval for Video Corpus Moment Retrieval"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3220-7263","authenticated-orcid":false,"given":"Yura","family":"Choi","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8689-3107","authenticated-orcid":false,"given":"Daechul","family":"Ahn","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7934-8434","authenticated-orcid":false,"given":"Jonghyun","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref2","article-title":"CLIP4Clip: An empirical study of CLIP for video-text retrieval","author":"Luo","year":"2021","journal-title":"arXiv:2104.08860"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref4","article-title":"Finding moments in video collections using natural language","author":"Escorcia","year":"2019","journal-title":"arXiv:1907.12763"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475281"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_11"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095182"},{"key":"ref9","article-title":"Learning language-visual embedding for movie understanding with natural-language","author":"Torabi","year":"2016","journal-title":"arXiv:1609.08124"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref11","article-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017","journal-title":"arXiv:1706.05098"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.173"},{"key":"ref13","first-page":"961","article-title":"Activitynet: A large-scale hierarchical video database for human activity analysis","volume-title":"Proc. CVPR","author":"Caba Heilbron"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1168"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747523"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25222"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.530"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00497"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"ref24","article-title":"Rethinking InfoNCE: How many negative samples do you need?","author":"Wu","year":"2021","journal-title":"arXiv:2105.13003"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186165"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.alvr-1.9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00673"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref29","first-page":"1311","article-title":"Automated curriculum learning for neural networks","volume-title":"Proc. ICML","author":"Graves"},{"key":"ref30","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref31","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref34","article-title":"Curriculum learning: A survey","author":"Soviany","year":"2021","journal-title":"arXiv:2101.10382"},{"key":"ref35","first-page":"2535","article-title":"On the power of curriculum learning in training deep networks","volume-title":"Proc. ICML","author":"Hacohen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00261"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.92"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.142"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3294567"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3316025"},{"key":"ref42","article-title":"A hierarchical multi-modal encoder for moment localization in video corpus","author":"Zhang","year":"2020","journal-title":"arXiv:2011.09046"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10902083.pdf?arnumber=10902083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T06:03:36Z","timestamp":1741241016000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10902083\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3542720","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}