{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:05:16Z","timestamp":1777889116393,"version":"3.51.4"},"reference-count":49,"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\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","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\/iccv51701.2025.01910","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20541-20550","source":"Crossref","is-referenced-by-count":0,"title":["Vid-Group: Temporal Video Grounding Pretraining from Unlabeled Videos in the Wild"],"prefix":"10.1109","author":[{"given":"Peijun","family":"Bao","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}]},{"given":"Chenqi","family":"Kong","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}]},{"given":"Siyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}]},{"given":"Zihao","family":"Shao","sequence":"additional","affiliation":[{"name":"Peking University"}]},{"given":"Xinghao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Jiaotong University"}]},{"given":"Boon Poh","family":"Ng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}]},{"given":"Meng Hwa","family":"Er","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}]},{"given":"Alex","family":"Kot","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref2","article-title":"Simbase: A simple baseline for temporal video grounding","author":"Bao","year":"2024","journal-title":"ArXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16175"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27831"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01137"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2021.3075470"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref9","article-title":"Trace: Temporal grounding video llm via causal event modeling","volume-title":"ICLR","author":"Guo","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27989"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00257"},{"key":"ref14","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma","year":"2014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00304"},{"key":"ref17","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3365249"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00538"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref24","article-title":"Howto 100 m: Learning a text-video embedding by watching hundred million narrated video clips","volume-title":"ICCV","author":"Miech","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_24"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00150"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2020.3048680"},{"key":"ref29","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0212-5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00636"},{"key":"ref35","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","volume-title":"ICLR","author":"Wang","year":"2024"},{"key":"ref36","article-title":"Hawkeye: Training video-text 1 ms for grounding text in videos","author":"Wang","year":"2024","journal-title":"ArXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00713"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/app14051894"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32971"},{"key":"ref40","article-title":"Pointsupervised video temporal grounding","author":"Xu","year":"2023","journal-title":"TMM"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3475723.3484247"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref45","article-title":"Autotvg: A new vision-language pre-training paradigm for temporal video grounding","author":"Zhang","year":"2024","journal-title":"ArXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.794"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_2"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3039886"}],"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\/11444517.pdf?arnumber=11444517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:35Z","timestamp":1777611995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444517\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01910","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}