{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:15:27Z","timestamp":1781723727160,"version":"3.54.5"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0100300"],"award-info":[{"award-number":["2018AAA0100300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172452"],"award-info":[{"award-number":["62172452"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3389024","type":"journal-article","created":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T17:30:35Z","timestamp":1713288635000},"page":"8896-8911","source":"Crossref","is-referenced-by-count":8,"title":["Modality-Aware Heterogeneous Graph for Joint Video Moment Retrieval and Highlight Detection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2712-4412","authenticated-orcid":false,"given":"Ruomei","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7891-4407","authenticated-orcid":false,"given":"Jiawei","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0179-9988","authenticated-orcid":false,"given":"Fuwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0751-5045","authenticated-orcid":false,"given":"Xiaonan","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8035-6737","authenticated-orcid":false,"given":"Yuanmao","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref2","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075470"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250518"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-08668-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01186"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3113505"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/139"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.337"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174136"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref24","first-page":"28442","article-title":"End-to-end multi-modal video temporal grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.120"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6988"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3110798"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00225"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.148"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref45","first-page":"1725","article-title":"Simple and deep graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref46","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref47","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref48","first-page":"5241","article-title":"GMNN: Graph Markov neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3226488"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref51","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref52","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref55","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_18"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00787"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00308"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_21"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00785"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.526"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.114"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10500395.pdf?arnumber=10500395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:39:06Z","timestamp":1736368746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10500395\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":77,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3389024","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}