{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:38Z","timestamp":1777865318155,"version":"3.51.4"},"reference-count":48,"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":"NSFC","doi-asserted-by":"publisher","award":["U22A2095,6247072922"],"award-info":[{"award-number":["U22A2095,6247072922"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018599","name":"Guangdong Provincial Key Laboratory of Information Security Technology","doi-asserted-by":"publisher","award":["2023B1212060026"],"award-info":[{"award-number":["2023B1212060026"]}],"id":[{"id":"10.13039\/501100018599","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\/iccv51701.2025.01861","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20009-20019","source":"Crossref","is-referenced-by-count":0,"title":["ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations"],"prefix":"10.1109","author":[{"given":"Tianming","family":"Liang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun-Yu","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaolei","family":"Tan","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianguo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian-Fang","family":"Hu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Grounded-SAM-2"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01234"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref11","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32387"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-6533-2_12"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref21","article-title":"Panoptic captioning: Seeking an equivalency bridge for image and text","author":"Lin","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref23","first-page":"26425","article-title":"Soc: semantic-assisted object cluster for referring video object segmentation","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Luo","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"ref28","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32806"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01789"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref41","article-title":"Youtube-vos: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28465"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0663"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01328"},{"key":"ref46","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref48","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint arXiv"}],"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\/11445597.pdf?arnumber=11445597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:15Z","timestamp":1777529715000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445597\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01861","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}