{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:46:06Z","timestamp":1766083566170,"version":"3.48.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Dalian High-Level Talents Innovation Support Plan","award":["2021RQ052"],"award-info":[{"award-number":["2021RQ052"]}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP210102674"],"award-info":[{"award-number":["DP210102674"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3618559","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:37:36Z","timestamp":1759772256000},"page":"9659-9669","source":"Crossref","is-referenced-by-count":0,"title":["Referring Video Object Segmentation With Cross-Modality Proxy Queries"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2861-4288","authenticated-orcid":false,"given":"Baoli","family":"Sun","sequence":"first","affiliation":[{"name":"DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0504-0186","authenticated-orcid":false,"given":"Xinzhu","family":"Ma","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong SAR, China"}]},{"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5011-9726","authenticated-orcid":false,"given":"Zhihui","family":"Wang","sequence":"additional","affiliation":[{"name":"DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8043-0312","authenticated-orcid":false,"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Sydney, Sydney, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13413-x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01234"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"ref14","first-page":"36324","article-title":"Decoupling features in hierarchical propagation for video object segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3469579"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3225720"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222643"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3281070"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00988"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32338"},{"article-title":"OpenSD: Unified open-vocabulary segmentation and detection","year":"2023","author":"Li","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"SeqFormer: A frustratingly simple model for video instance segmentation","year":"2021","author":"Wu","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00028"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"ref30","first-page":"31265","article-title":"MinVIS: A minimal video instance segmentation framework without video-based training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01106"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3241802"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163578"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3305869"},{"article-title":"Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation","year":"2021","author":"Liang","key":"ref36"},{"article-title":"RoBERTa: A robustly optimized BERT pretraining approach","year":"2019","author":"Liu","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-7131-2_100141"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref40","first-page":"263","article-title":"Referring expression object segmentation with caption-aware consistency","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Chen","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00425"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475534"},{"article-title":"The 2017 DAVIS challenge on video object segmentation","year":"2017","author":"Pont-Tuset","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110535"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103566"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00548"},{"key":"ref52","first-page":"26425","article-title":"SOC: Semantic-assisted object cluster for referring video object segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Luo","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00061"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054384"},{"article-title":"ClawCraneNet: Leveraging object-level relation for text-based video segmentation","year":"2021","author":"Liang","key":"ref56"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11194253.pdf?arnumber=11194253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:34:21Z","timestamp":1766082861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11194253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3618559","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}