{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:55:34Z","timestamp":1763060134494,"version":"3.45.0"},"reference-count":57,"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":["62276046","62431004","62406055"],"award-info":[{"award-number":["62276046","62431004","62406055"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Dalian Science and Technology Innovation Foundation","award":["2023JJ12GX015"],"award-info":[{"award-number":["2023JJ12GX015"]}]},{"name":"Science and Technology Program Joint Project of Liaoning Province","award":["2024JH2\/102600090"],"award-info":[{"award-number":["2024JH2\/102600090"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3604944","type":"journal-article","created":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:31:31Z","timestamp":1756755091000},"page":"8045-8055","source":"Crossref","is-referenced-by-count":0,"title":["CollabLearn: Propelling Weakly-Supervised Referring Image Segmentation Through Collaboration Between Semantics and Details"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9680-9624","authenticated-orcid":false,"given":"Chao","family":"Jiang","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2168-204X","authenticated-orcid":false,"given":"Yuqiu","family":"Kong","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8319-4266","authenticated-orcid":false,"given":"Mengnan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9241-1688","authenticated-orcid":false,"given":"Lihe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3121-1823","authenticated-orcid":false,"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00909"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_36"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01281"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00248"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163578"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01425"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01999"},{"article-title":"Weakly-supervised segmentation of referring expressions","year":"2022","author":"Strudel","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref14","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":"ref15","article-title":"Improving object-centric learning with query optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jia","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.,","volume":"139","author":"Radford","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358085"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3305869"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.12.018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01507"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28148"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_16"},{"key":"ref31","first-page":"33754","article-title":"Reco: Retrieve and co-segment for zero-shot transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shin","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058684"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186410"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01387"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00425"},{"key":"ref39","article-title":"Boosting weakly-supervised referring image segmentation via progressive comprehension","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Yang","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00402"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28172"},{"key":"ref43","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Zeng","year":"2022"},{"key":"ref44","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"article-title":"Categorical reparameterization with gumbel-softmax","year":"2017","author":"Jang","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5034"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01864"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00746"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01369"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00431"},{"key":"ref55","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11146530.pdf?arnumber=11146530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:44:43Z","timestamp":1763059483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11146530\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3604944","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}