{"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":1783736905797,"version":"3.55.0"},"reference-count":75,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62172089"],"award-info":[{"award-number":["62172089"]}],"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":["62172090"],"award-info":[{"award-number":["62172090"]}],"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":["62106045"],"award-info":[{"award-number":["62106045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Jiangsu province","award":["BK20191258"],"award-info":[{"award-number":["BK20191258"]}]},{"name":"Australian Research Council Future Fellowship Award","award":["FT210100268"],"award-info":[{"award-number":["FT210100268"]}]},{"name":"Jiangsu Provincial Key Laboratory of Computer Networking Technology"},{"name":"Jiangsu Provincial Key Laboratory of Network and Information Security","award":["BM2003201"],"award-info":[{"award-number":["BM2003201"]}]},{"name":"Key Laboratory of Computer Network and Information Integration of Ministry of Education of China","award":["93K-9"],"award-info":[{"award-number":["93K-9"]}]},{"name":"Nanjing Purple Mountain Laboratory"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3581797","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T13:29:00Z","timestamp":1750426140000},"page":"6296-6306","source":"Crossref","is-referenced-by-count":6,"title":["Context-Enhanced Video Moment Retrieval With Large Language Models"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2634-7283","authenticated-orcid":false,"given":"Weijia","family":"Liu","sequence":"first","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3025-4429","authenticated-orcid":false,"given":"Bo","family":"Miao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Software Engineering, University of Western Australia, Perth, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2448-6717","authenticated-orcid":false,"given":"Jiuxin","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7676-2843","authenticated-orcid":false,"given":"Xuelin","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7268-7815","authenticated-orcid":false,"given":"Jiawei","family":"Ge","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5209-9063","authenticated-orcid":false,"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehwish","family":"Nasim","sequence":"additional","affiliation":[{"name":"School of Computer Science and Software Engineering, University of Western Australia, Perth, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5206-3842","authenticated-orcid":false,"given":"Ajmal","family":"Mian","sequence":"additional","affiliation":[{"name":"School of Computer Science and Software Engineering, University of Western Australia, Perth, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3334019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238514"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3309551"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222664"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3316025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222965"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063631"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142420"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3395888"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310282"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01186"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3250088"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01248"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414053"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3038993"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.085"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref23","first-page":"28442","article-title":"End-to-end multi-modal video temporal grounding","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref26","article-title":"GPT-4 technical report","author":"OpenAI","year":"2023"},{"key":"ref27","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac","year":"2022"},{"key":"ref28","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref29","article-title":"Videochat: Chat-centric video understanding","author":"Li","year":"2025","journal-title":"Sci. China Inf. Sci."},{"key":"ref30","article-title":"M3IT: A large-scale dataset towards multi-modal multilingual instruction tuning","author":"Li","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00035"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01456"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02214-4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00695"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00304"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414026"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01038"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075470"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_36"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3701733"},{"key":"ref48","first-page":"76749","article-title":"Self-chained image-language model for video localization and question answering","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"36","author":"Yu","year":"2024"},{"key":"ref49","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref50","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref51","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Lei","year":"2021"},{"key":"ref52","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref54","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01105"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01263"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01253"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref65","first-page":"65948","article-title":"MomentDiff: Generative video moment retrieval from random to real","volume-title":"Proc. Annu. Conf. neural Inf. Process. Syst.","volume":"36","author":"Li","year":"2023"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28177"},{"key":"ref67","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref68","article-title":"ADAM: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00225"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"ref73","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_8"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11045538.pdf?arnumber=11045538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:20:14Z","timestamp":1759234814000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11045538\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3581797","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}