{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:59:55Z","timestamp":1783529995300,"version":"3.55.0"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["62206157"],"award-info":[{"award-number":["62206157"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276155"],"award-info":[{"award-number":["62276155"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206156"],"award-info":[{"award-number":["62206156"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2022QF047"],"award-info":[{"award-number":["ZR2022QF047"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tcsvt.2024.3508752","type":"journal-article","created":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T19:00:34Z","timestamp":1732906834000},"page":"3234-3249","source":"Crossref","is-referenced-by-count":19,"title":["CMIRNet: Cross-Modal Interactive Reasoning Network for Referring Image Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1492-0970","authenticated-orcid":false,"given":"Mingzhu","family":"Xu","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxiang","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1344-2513","authenticated-orcid":false,"given":"Haoyu","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5653-8286","authenticated-orcid":false,"given":"Yupeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172423"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3236320"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00909"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3010181"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475222"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3340062"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref21","article-title":"Rethinking Atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20108"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3292285"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26325"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163578"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074008"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231964"},{"key":"ref32","first-page":"1","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00080"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311618"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00335"},{"key":"ref36","first-page":"19769","article-title":"Segment everything everywhere all at once","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zou"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00332"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref39","article-title":"RefVOS: A closer look at referring expressions for video object segmentation","author":"Bellver","year":"2020","journal-title":"arXiv:2010.00263"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3023438"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3605781"},{"key":"ref45","first-page":"14729","article-title":"Coupalign: Coupling word-pixel with sentence-mask alignments for referring image segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang"},{"key":"ref46","first-page":"26425","article-title":"SOC: Semantic-assisted object cluster for referring video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Luo"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612117"},{"key":"ref49","first-page":"1","article-title":"Spectral networks and locally connected networks on graphs","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Bruna"},{"key":"ref50","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Defferrard"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01157"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_35"},{"key":"ref53","article-title":"Joint visual grounding with language scene graphs","author":"Liu","year":"2019","journal-title":"arXiv:1906.03561"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3090167"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01509"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00897"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083269"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3300317"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2009.03.008"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263468"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277791"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3308550"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3281372"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref77","article-title":"EVF-SAM: Early vision-language fusion for text-prompted segment anything model","author":"Zhang","year":"2024","journal-title":"arXiv:2406.20076"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10949577\/10771801.pdf?arnumber=10771801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T22:13:05Z","timestamp":1744063985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10771801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":77,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3508752","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}