{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:31:43Z","timestamp":1785857503923,"version":"3.56.0"},"reference-count":60,"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\/501100001666","name":"The National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372014,62525201,62132001,62432001"],"award-info":[{"award-number":["62372014,62525201,62132001,62432001"]}],"id":[{"id":"10.13039\/501100001666","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\/iccv51701.2025.02005","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21589-21599","source":"Crossref","is-referenced-by-count":2,"title":["Hierarchical Event Memory for Accurate and Low-Latency Online Video Temporal Grounding"],"prefix":"10.1109","author":[{"given":"Minghang","family":"Zheng","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxin","family":"Peng","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benyuan","family":"Sun","sequence":"additional","affiliation":[{"name":"Central Media Technology Institute,Huawei"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Central Media Technology Institute,Huawei"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.58769\/joinssr.1262853"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00949"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00956"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01930"},{"key":"ref5","article-title":"Enhancing long video understanding via hierarchical event-based memory","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00245"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00089"},{"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","article-title":"Neural networks: a comprehensive foundation","author":"Haykin","year":"1994","journal-title":"Prentice Hall PTR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_41"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01347"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_37"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2021.00.093"},{"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\/ICCV.2017.324"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28177"},{"key":"ref24","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02207"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00538"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01791"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01082"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01266"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2705068"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3792"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_12"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref35","first-page":"5","article-title":"Online action detection in untrimmed, streaming videos-modeling and evaluation","author":"Shou","year":"2018","journal-title":"In ECCV"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref39","first-page":"3","article-title":"Gomez, \u0141ukasz Kaiser, and Illia Polosukhin","volume":"30","author":"Vaswani","year":"2017","journal-title":"Attention is all you need. Advances in neural information processing systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.556"},{"key":"ref42","article-title":"Videollamb: Long-context video understanding with recurrent memory bridges","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00563"},{"key":"ref47","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01573"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.173"},{"key":"ref50","article-title":"Flash-vstream: Memorybased real-time understanding for long video streams","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108741"},{"key":"ref53","article-title":"and Philipp Kr\u00e4henb\u00fchl","volume-title":"Real-time online video detection with temporal smoothing transformers. In European Conference on Computer Vision (ECCV)","author":"Zhao"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2021.00.455"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20263"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01511"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.794"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25478"},{"key":"ref59","article-title":"Training-free video temporal grounding usinglarge-scale pre-trained models","volume-title":"In Proceedings of the European Conference on Computer Vision (ECCV)","author":"Zheng"},{"key":"ref60","first-page":"34","author":"Zheng","year":"2020","journal-title":"DistanceIoU Loss. Faster and better learning for bounding box regression"}],"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\/11443421.pdf?arnumber=11443421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:42Z","timestamp":1777530162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02005","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}