{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:50:01Z","timestamp":1783738201542,"version":"3.55.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":["62272144"],"award-info":[{"award-number":["62272144"]}],"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":["72188101"],"award-info":[{"award-number":["72188101"]}],"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":["62020106007"],"award-info":[{"award-number":["62020106007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2408085J040"],"award-info":[{"award-number":["2408085J040"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Project of Anhui Province","award":["202203a05020011"],"award-info":[{"award-number":["202203a05020011"]}]},{"name":"Major Project of Anhui Province","award":["202423k09020001"],"award-info":[{"award-number":["202423k09020001"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JZ2024HGTG0309"],"award-info":[{"award-number":["JZ2024HGTG0309"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JZ2024AHST0337"],"award-info":[{"award-number":["JZ2024AHST0337"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JZ2023YQTD0072"],"award-info":[{"award-number":["JZ2023YQTD0072"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"New Cornerstone Science Foundation"},{"name":"XPLORER PRIZE"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tpami.2025.3558854","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T17:39:46Z","timestamp":1744133986000},"page":"6445-6462","source":"Crossref","is-referenced-by-count":10,"title":["Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Grounding"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6944-0848","authenticated-orcid":false,"given":"Jingjing","family":"Hu","sequence":"first","affiliation":[{"name":"Key Laboratory of Knowledge Engineering with Big Data (HFUT), Ministry of Education, School of Computer Science and Information Engineering (School of Artificial Intelligence), Hefei University of Technology (HFUT), and Intelligent Interconnected Systems Laboratory of Anhui Province (HFUT), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2594-254X","authenticated-orcid":false,"given":"Dan","family":"Guo","sequence":"additional","affiliation":[{"name":"Key Laboratory of Knowledge Engineering with Big Data (HFUT), Ministry of Education, School of Computer Science and Information Engineering (School of Artificial Intelligence), Hefei University of Technology (HFUT), and Intelligent Interconnected Systems Laboratory of Anhui Province (HFUT), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5083-2145","authenticated-orcid":false,"given":"Kun","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Knowledge Engineering with Big Data (HFUT), Ministry of Education, School of Computer Science and Information Engineering (School of Artificial Intelligence), Hefei University of Technology (HFUT), and Intelligent Interconnected Systems Laboratory of Anhui Province (HFUT), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4517-3509","authenticated-orcid":false,"given":"Zhan","family":"Si","sequence":"additional","affiliation":[{"name":"Department of Chemistry and Centre for Atomic Engineering of Advanced Materials, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-1638","authenticated-orcid":false,"given":"Xun","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-8807","authenticated-orcid":false,"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Knowledge Engineering with Big Data (HFUT), Ministry of Education, School of Computer Science and Information Engineering (School of Artificial Intelligence), Hefei University of Technology (HFUT), and Intelligent Interconnected Systems Laboratory of Anhui Province (HFUT), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-020-01003-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-020-0644-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547996"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.140"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16285"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238514"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414026"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250518"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3120745"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25478"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3060449"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547782"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01248"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01511"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.324"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3052086"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531394"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3543857"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3038993"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532083"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.611"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3783-3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3261927"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref35","article-title":"Temporal localization of moments in video collections with natural language","author":"Escorcia","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref38","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lei"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref42","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref43","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref44","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref45","first-page":"10937","article-title":"UniSpeech: Unified speech representation learning with labeled and unlabeled data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref50","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref51","article-title":"One-peace: Exploring one general representation model toward unlimited modalities","author":"Wang","year":"2023"},{"key":"ref52","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref53","article-title":"COCA: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref54","article-title":"Graph attention networks","author":"Velickovic","year":"2017"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"ref56","first-page":"991","article-title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sch\u00fctt"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"ref61","article-title":"Scaling speech technology to 1, 000 languages","author":"Pratap","year":"2023"},{"key":"ref62","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612401"},{"key":"ref64","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref67","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.77"},{"key":"ref69","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021"},{"key":"ref70","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983349"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn60899.2024.10650814"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11068886\/10955430.pdf?arnumber=10955430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T17:38:32Z","timestamp":1751996312000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10955430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":76,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3558854","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}