{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T19:10:59Z","timestamp":1766171459884,"version":"3.48.0"},"reference-count":65,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976034"],"award-info":[{"award-number":["61976034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017683","name":"Dalian Science and Technology Innovation Fund","doi-asserted-by":"publisher","award":["2022JJ12GX013"],"award-info":[{"award-number":["2022JJ12GX013"]}],"id":[{"id":"10.13039\/501100017683","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","award":["2022-YGJC20"],"award-info":[{"award-number":["2022-YGJC20"]}],"id":[{"id":"10.13039\/501100005047","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.2025.3618539","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:46:21Z","timestamp":1759859181000},"page":"9749-9760","source":"Crossref","is-referenced-by-count":0,"title":["P$^{2}$M: Progressive Perspective Mining for Referring Video Object Segmentation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5295-1508","authenticated-orcid":false,"given":"Yihan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2861-4288","authenticated-orcid":false,"given":"Baoli","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0504-0186","authenticated-orcid":false,"given":"Xinzhu","family":"Ma","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8937-1515","authenticated-orcid":false,"given":"Hongwei","family":"Ge","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiulin","family":"Fan","sequence":"additional","affiliation":[{"name":"Huadian Coal Group Digital Intelligence Technology Company, Huadian Coal Industry Group Company Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3882-2205","authenticated-orcid":false,"given":"Haojie","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong Science and Technology, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"article-title":"Reframe anything: LLM agent for open world video reframing","year":"2024","author":"Cao","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183402"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0212-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3305869"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3340062"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358085"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163578"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref13","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2021","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01328"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01234"},{"key":"ref17","first-page":"11525","article-title":"Object-centric learning with slot attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Locatello","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01864"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01999"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01520"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00159"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7008"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref33","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859966"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054384"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00417"},{"article-title":"Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation","year":"2021","author":"Liang","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3185487"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref41","article-title":"spaCy: Industrial-strength natural language processing in Python","author":"Honnibal","year":"2020","journal-title":"Zenodo"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2068"},{"key":"ref43","first-page":"1218","article-title":"RoBERTA: A robustly optimized bert pretraining approach","author":"Liu","year":"2021","journal-title":"Proc. 20th Chin. Nat. Conf. Comput. Linguistics"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00491"},{"article-title":"ClawCraneNet: Leveraging object-level relation for text-based video segmentation","year":"2021","author":"Liang","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547761"},{"key":"ref52","first-page":"26425","article-title":"SOC: Semantic-assisted object cluster for referring video object segmentation","volume-title":"Proc. 37 Int. Conf. Neural Inf. Process. Syst.","author":"Luo","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref54","first-page":"7","article-title":"Progressive multimodal interaction network for referring video object segmentation","volume-title":"Proc. 3rd Large-Scale Video Object Segmentation Challenge","author":"Ding","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02032"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"article-title":"RoBertA: A robustly optimized BERT pretraining approach","year":"2019","author":"Liu","key":"ref62"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11195738.pdf?arnumber=11195738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T18:59:37Z","timestamp":1766170777000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11195738\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3618539","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}