{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:28:26Z","timestamp":1783736906304,"version":"3.55.0"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62202311"],"award-info":[{"award-number":["62202311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2023A1515011512"],"award-info":[{"award-number":["2023A1515011512"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01959","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21085-21096","source":"Crossref","is-referenced-by-count":2,"title":["OVG-HQ: Online Video Grounding with Hybrid-Modal Queries"],"prefix":"10.1109","author":[{"given":"Runhao","family":"Zeng","sequence":"first","affiliation":[{"name":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Mao","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghao","family":"Lai","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minh Hieu","family":"Phan","sequence":"additional","affiliation":[{"name":"University of Adelaide"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanjie","family":"Dong","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Adelaide"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiping","family":"Hu","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.773"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01930"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00245"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_17"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2022.109329"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612120"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref13","first-page":"1984","article-title":"Excl: Extractive clip localization using natural language descriptions","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies","volume":"1","author":"Ghosh","year":"2019"},{"key":"ref14","article-title":"Minotaur: Multi-task video grounding from multimodal queries","author":"Goyal","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_41"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_37"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_13"},{"key":"ref19","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01105"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2880"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00262"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20058"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref26","first-page":"421","article-title":"R2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Liu","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02207"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00538"},{"key":"ref30","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01791"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01082"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00191"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","first-page":"2980","article-title":"Focal loss for dense object detection","volume-title":"proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","author":"Ross","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"ref42","article-title":"Learning to (learn at test time): Rnns with expressive hidden states","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00695"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref50","first-page":"1086","article-title":"Long short-term transformer for online action detection","volume":"34","author":"Xu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/app14051894"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650814"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01253"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01733"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"ref56","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3038993"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3475723.3484247"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_17"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00317"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.69"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350879"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/610"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_2"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612468"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443390.pdf?arnumber=11443390","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:42:48Z","timestamp":1777610568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443390\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01959","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}