{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T21:10:27Z","timestamp":1778274627632,"version":"3.51.4"},"reference-count":52,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01926","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20715-20725","source":"Crossref","is-referenced-by-count":1,"title":["Open-Ended Hierarchical Streaming Video Understanding with Vision Language Models"],"prefix":"10.1109","author":[{"given":"Hyolim","family":"Kang","sequence":"first","affiliation":[{"name":"Yonsei University"}]},{"given":"Yunsu","family":"Park","sequence":"additional","affiliation":[{"name":"Yonsei University"}]},{"given":"Youngbeom","family":"Yoo","sequence":"additional","affiliation":[{"name":"Yonsei University"}]},{"given":"Yeeun","family":"Choi","sequence":"additional","affiliation":[{"name":"Yonsei University"}]},{"given":"Seon Joo","family":"Kim","sequence":"additional","affiliation":[{"name":"Yonsei University"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00949"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_38"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01930"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref7","article-title":"R-fcn: Object detection via region-based fully convolutional networks","author":"Dai","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00089"},{"key":"ref11","author":"Farebrother","year":"2024","journal-title":"Stop regressing: Training value functions via classification for scalable deep rl"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref14","author":"Imani","year":"2024","journal-title":"Investigating the histogram loss in regression"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01723"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01347"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_22"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_37"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108871"},{"key":"ref21","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_1"},{"key":"ref24","article-title":"Et bench: Towards open-ended eventlevel video-language understanding","author":"Liu","year":"2024","journal-title":"In Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref26","author":"Pei","year":"2024","journal-title":"Egovideo: Exploring egocentric foundation model and downstream adaptation"},{"key":"ref27","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_12"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01722"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1688"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref37","author":"Tuan","year":"2022","journal-title":"Simon: A simple framework for online temporal action localization"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01271"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref41","author":"Wu","year":"2024","journal-title":"Videollm-mod: Efficient video-language streaming with mixture-of-depths vision computation"},{"key":"ref42","author":"Xu","year":"2024","journal-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00563"},{"key":"ref44","article-title":"Long short-term transformer for online action detection","author":"Xu","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00316"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1518"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_28"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01727"},{"key":"ref52","author":"Zhu","year":"2023","journal-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models"}],"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\/11444898.pdf?arnumber=11444898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:25:48Z","timestamp":1777613148000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444898\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01926","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}