{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:28:13Z","timestamp":1783542493647,"version":"3.55.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["62371343"],"award-info":[{"award-number":["62371343"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3671127","type":"journal-article","created":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T20:45:57Z","timestamp":1772743557000},"page":"9821-9834","source":"Crossref","is-referenced-by-count":0,"title":["Structure-Preserved Superpixel Perception for Referring Image Segmentation"],"prefix":"10.1109","volume":"36","author":[{"given":"Ran","family":"Chen","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, the School of Computer Science and Technology, and the Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4357-1095","authenticated-orcid":false,"given":"Taiyi","family":"Su","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, the School of Computer Science and Technology, and the Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1048-4574","authenticated-orcid":false,"given":"Shanshan","family":"Du","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, the School of Computer Science and Technology, and the Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-4871","authenticated-orcid":false,"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, the School of Computer Science and Technology, and the Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3010181"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27896"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231964"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263468"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_22"},{"key":"ref16","article-title":"Vision transformer with super token sampling","author":"Huang","year":"2022","journal-title":"arXiv:2211.11167"},{"key":"ref17","article-title":"SPFormer: Enhancing vision transformer with superpixel representation","author":"Mei","year":"2024","journal-title":"arXiv:2401.02931"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3508752"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref23","first-page":"13","article-title":"ViLBERT: Pretraining task agnostic vision-linguistic representations for vision-and-language tasks","volume-title":"Proc. NeurIPS","author":"Lu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3240472"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"ref26","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25428"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3340062"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238308"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995323"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00066"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00259"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3371348"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref45","first-page":"4467","article-title":"Dual path networks","volume-title":"Proc. NeurIPS","author":"Chen"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163578"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref60","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110719"},{"key":"ref62","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref64","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref67","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11422003.pdf?arnumber=11422003","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:45:41Z","timestamp":1783539941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11422003\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":67,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3671127","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}