{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T01:26:05Z","timestamp":1773883565988,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Natural Science Fund of China","doi-asserted-by":"publisher","award":["U25A20527"],"award-info":[{"award-number":["U25A20527"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Natural Science Fund of China","doi-asserted-by":"publisher","award":["62473286"],"award-info":[{"award-number":["62473286"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010256","name":"Shanghai Municipal Science and Technology Major Project","doi-asserted-by":"publisher","award":["2025SHZDZX025G10"],"award-info":[{"award-number":["2025SHZDZX025G10"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3671609","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:40:22Z","timestamp":1773348022000},"page":"2714-2726","source":"Crossref","is-referenced-by-count":0,"title":["ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Grounding"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1640-4504","authenticated-orcid":false,"given":"Yubin","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4991-0596","authenticated-orcid":false,"given":"Xinyang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4603-847X","authenticated-orcid":false,"given":"De","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3103-8442","authenticated-orcid":false,"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6745-9674","authenticated-orcid":false,"given":"Cairong","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3117472"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01365"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_3"},{"key":"ref6","article-title":"VideoLLM: Modeling video sequence with large language models","author":"Chen","year":"2023","journal-title":"arXiv:2305.13292"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.324"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref12","first-page":"1984","article-title":"EXCL: Extractive clip localization using natural language descriptions","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Ghosh"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.114"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.318"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_21"},{"key":"ref17","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref18","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681115"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref22","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lei"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16285"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref28","article-title":"Probing visual-audio representation for video highlight detection via hard-pairs guided contrastive learning","author":"Li","year":"2022","journal-title":"arXiv:2206.10157"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02207"},{"key":"ref38","article-title":"Correlation-guided query-dependency calibration for video temporal grounding","author":"Moon","year":"2023","journal-title":"arXiv:2311.08835"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00191"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"issue":"8","key":"ref43","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_16"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0944"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00636"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28387"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref53","article-title":"InternVideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv:2212.03191"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00308"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00787"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3191841"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01253"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.526"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00785"},{"key":"ref64","first-page":"23634","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Zellers"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3060449"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3362062"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_2"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11433530.pdf?arnumber=11433530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:41:40Z","timestamp":1773862900000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433530\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3671609","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}