{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:02:06Z","timestamp":1777888926526,"version":"3.51.4"},"reference-count":51,"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":["62471064"],"award-info":[{"award-number":["62471064"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.02207","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23773-23783","source":"Crossref","is-referenced-by-count":0,"title":["VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-Based Group Relative Policy Optimization"],"prefix":"10.1109","author":[{"given":"Xinye","family":"Cao","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongcan","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawen","family":"Qian","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoshun","family":"Nan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqi","family":"Pan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianhao","family":"Hou","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutong","family":"Gao","sequence":"additional","affiliation":[{"name":"Minzu University of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.807"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref6","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","volume":"abs\/2412.05271","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018247"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00135"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29748"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01778"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"ref12","article-title":"Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal 11 ms in video analysis","volume":"abs\/2405.21075","author":"Fu","year":"2024","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148868"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01723"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3143699"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.141"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3792"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3331846"},{"key":"ref28","article-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","volume":"abs\/2402.03300","author":"Shao","year":"2024","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00558"},{"key":"ref31","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","volume":"abs\/2409.12191","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3523798"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref35","article-title":"Lifelongmemory: Leveraging 11 ms for answering queries in egocentric videos","volume":"abs\/2312.05269","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref36","article-title":"Videotree: Adaptive tree-based video representation for LLM reasoning on long videos","volume":"abs\/2405.19209","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0907"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"ref39","article-title":"Next-gpt: Any-to-any multimodal LLM","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Wu","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2801826"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2920899"},{"key":"ref47","article-title":"Video instruction tuning with synthetic data","volume":"abs\/2410.02713","author":"Zhang","year":"2024","journal-title":"CoRR"},{"key":"ref48","article-title":"Videoprism: A foundational visual encoder for video understanding","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Zhao","year":"2024"},{"key":"ref49","article-title":"MLVU: A comprehensive benchmark for multi-task long video understanding","volume":"abs\/2406.04264","author":"Zhou","year":"2024","journal-title":"CoRR"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3176413"}],"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\/11445201.pdf?arnumber=11445201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:02:37Z","timestamp":1777611757000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02207","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}