{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:29Z","timestamp":1777890209768,"version":"3.51.4"},"reference-count":64,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0161200,2022ZD0161201"],"award-info":[{"award-number":["2022ZD0161200,2022ZD0161201"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002918","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["24200223"],"award-info":[{"award-number":["24200223"]}],"id":[{"id":"10.13039\/501100002918","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003058","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","award":["ITS\/228\/22FP"],"award-info":[{"award-number":["ITS\/228\/22FP"]}],"id":[{"id":"10.13039\/501100003058","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\/iccv51701.2025.00876","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9385-9395","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained Spatiotemporal Grounding on Egocentric Videos"],"prefix":"10.1109","author":[{"given":"Shuo","family":"Liang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiwu","family":"Zhong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zi-Yuan","family":"Hu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeyao","family":"Tao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liwei","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0219"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1684"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref6","article-title":"Epic-kitchens visor benchmark: Video segmentations and object relations","volume-title":"Proceedings of the Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks","author":"Darkhalil","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01229"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01735"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref15","author":"Ji","year":"2024","journal-title":"ISAT with Segment Anything: An Interactive Semi-Automatic Annotation Tool"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2117"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01396"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref22","article-title":"Qvhighlights: Detecting moments and highlights in videos via natural language queries","volume":"abs\/2107.09609","author":"Lei","year":"2021","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02032"},{"key":"ref24","article-title":"Egocentric video-language pre-training","volume-title":"NeurIPS","author":"Lin","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref28","article-title":"Decoupled weight decay regularization","volume-title":"ICLR (Poster)","author":"Loshchilov","year":"2019"},{"key":"ref29","article-title":"Egoschema: A diagnostic benchmark for very longform video language understanding","volume-title":"NeurIPS","author":"Mangalam","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"ref32","article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","volume-title":"NeurIPS","author":"Mu","year":"2023"},{"key":"ref33","year":"2024","journal-title":"OpenAI. Hello gpt-4o"},{"key":"ref34","article-title":"Egovideo: Exploring egocentric foundation model and downstream adaptation","volume":"abs\/2406.18070","author":"Pei","year":"2024","journal-title":"CoRR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02095-7"},{"key":"ref37","article-title":"The 2017 DAVIS challenge on video object segmentation","volume":"abs\/1704.00675","author":"Pont-Tuset","year":"2017","journal-title":"CoRR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref40","author":"Rasheed","year":"2024","journal-title":"Llava++: extending visual capabilities with llama-3 and phi-3 (2024)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref42","article-title":"SAM 2: Segment anything in images and videos","volume":"abs\/2408.00714","author":"Ravi","year":"2024","journal-title":"CoRR"},{"key":"ref43","author":"Ren","year":"2024","journal-title":"Grounded sam: Assembling open-world models for diverse visual tasks"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref45","article-title":"Ego4d goal-step: Toward hierarchical understanding of procedural activities","volume-title":"NeurIPS","author":"Song","year":"2023"},{"key":"ref46","article-title":"Egotracks: A long-term egocentric visual object tracking dataset","volume-title":"NeurIPS","author":"Tang","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"key":"ref48","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref53","article-title":"Youtube-vos: A large-scale video object segmentation benchmark","volume":"abs\/1809.03327","author":"Xu","year":"2018","journal-title":"CoRR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3391743"},{"key":"ref56","article-title":"Mm-ego: Towards building egocentric multimodal 11 ms","volume":"abs\/2410.07177","author":"Ye","year":"2024","journal-title":"CoRR"},{"key":"ref57","author":"Yu","year":"2023","journal-title":"Mm -vet: Evaluating large multimodal models for integrated capabilities"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref59","article-title":"Sa2va: Marrying SAM2 with llava for dense grounded understanding of images and videos","volume":"abs\/2501.04001","author":"Yuan","year":"2025","journal-title":"CoRR"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00913"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.391"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"}],"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\/11445169.pdf?arnumber=11445169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:42Z","timestamp":1777613502000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00876","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}