{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T11:06:42Z","timestamp":1777633602807,"version":"3.51.4"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003009","name":"Science and Technology Development Fund","doi-asserted-by":"publisher","award":["0071\/2022\/A"],"award-info":[{"award-number":["0071\/2022\/A"]}],"id":[{"id":"10.13039\/501100003009","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China, Youth Fund","award":["62102318"],"award-info":[{"award-number":["62102318"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3316025","type":"journal-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:41:45Z","timestamp":1694799705000},"page":"3799-3813","source":"Crossref","is-referenced-by-count":14,"title":["Cross-Modality Knowledge Calibration Network for Video Corpus Moment Retrieval"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7719-8364","authenticated-orcid":false,"given":"Tongbao","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2664-4413","authenticated-orcid":false,"given":"Wenmin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9471-9651","authenticated-orcid":false,"given":"Zhe","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4341-6474","authenticated-orcid":false,"given":"Ruochen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2603-8328","authenticated-orcid":false,"given":"Bingshu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"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":"10.1109\/TMM.2021.3120545"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3168424"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142420"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref9","article-title":"CLEVRER: Collision events for video representation and reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yi","year":"2020"},{"key":"ref10","article-title":"Grounding physical concepts of objects and events through dynamic visual reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref11","article-title":"Temporal localization of moments in video collections with natural language","author":"Escorcia","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.444"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2647386"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079025"},{"key":"ref15","article-title":"Vireo @, TRecViD 2017: Video-to-text, ad-hoc video search and video hyperlinking","volume-title":"Proc. TREC Video Retrieval Eval.","author":"Nguyen","year":"2017"},{"key":"ref16","article-title":"A hierarchical multi-modal encoder for moment localization in video corpus","author":"Zhang","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475281"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747523"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"ref29","first-page":"1984","article-title":"ExCL: Extractive clip localization using natural language descriptions","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technol.","volume":"1","author":"Ghosh","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3023339"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.085"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20058"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00695"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3222664"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029181"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00506"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref50","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.733"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1078"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10252035.pdf?arnumber=10252035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:23:54Z","timestamp":1710404634000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10252035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3316025","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}