{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T20:57:07Z","timestamp":1767646627689,"version":"3.48.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100017677","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["KJZD20240903100501002"],"award-info":[{"award-number":["KJZD20240903100501002"]}],"id":[{"id":"10.13039\/501100017677","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017677","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["KJZD20230923114810022"],"award-info":[{"award-number":["KJZD20230923114810022"]}],"id":[{"id":"10.13039\/501100017677","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017677","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["JCYJ20220818103006012"],"award-info":[{"award-number":["JCYJ20220818103006012"]}],"id":[{"id":"10.13039\/501100017677","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017677","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["ZDSYS20220606100601002"],"award-info":[{"award-number":["ZDSYS20220606100601002"]}],"id":[{"id":"10.13039\/501100017677","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019443","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2023A1515011347"],"award-info":[{"award-number":["2023A1515011347"]}],"id":[{"id":"10.13039\/501100019443","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society"},{"name":"Longang District Shenzhen\u2019s \u201cTen Action Plan\u201d for Supporting Innovation Projects","award":["LGKCSDPT 2024002"],"award-info":[{"award-number":["LGKCSDPT 2024002"]}]},{"name":"Longang District Shenzhen\u2019s \u201cTen Action Plan\u201d for Supporting Innovation Projects","award":["2024003"],"award-info":[{"award-number":["2024003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tcsvt.2025.3546634","type":"journal-article","created":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T13:57:57Z","timestamp":1740751077000},"page":"8148-8160","source":"Crossref","is-referenced-by-count":1,"title":["MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7801-4627","authenticated-orcid":false,"given":"Long","family":"Xu","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Artiffcial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2493-6033","authenticated-orcid":false,"given":"Yongquan","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artiffcial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4869-5174","authenticated-orcid":false,"given":"Shanghong","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artiffcial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3361076"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3368053"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3320688"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/rs15030801"},{"key":"ref5","article-title":"Empowering segmentation ability to multi-modal large language models","author":"Yang","year":"2024","journal-title":"arXiv:2403.14141"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3378000"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3295062"},{"key":"ref8","first-page":"1","article-title":"Evidential uncertainty and diversity guided active learning for scene graph generation","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Sun"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3285009"},{"key":"ref10","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. NIPS","volume":"34","author":"Cheng"},{"key":"ref11","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref12","first-page":"1","article-title":"Segment anything in high quality","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lei"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref14","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Sys. (NIPS)","volume":"34","author":"Xie"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00136"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02037"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref21","article-title":"HRSAM: Efficient interactive segmentation in high-resolution images","author":"Huang","year":"2024","journal-title":"arXiv:2407.02109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref23","article-title":"Structured click control in transformer-based interactive segmentation","author":"Xu","year":"2024","journal-title":"arXiv:2405.04009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00362"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00180"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897365"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16752"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.10.009"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01393"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278410"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00238"},{"key":"ref35","first-page":"1","article-title":"QuadTree attention for vision transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3221611"},{"issue":"120","key":"ref37","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00865"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.47"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref45","first-page":"1","article-title":"LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","volume":"1","author":"Wang"},{"key":"ref46","article-title":"Faster segment anything: Towards lightweight SAM for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv:2306.14289"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11114024\/10908400.pdf?arnumber=10908400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:55Z","timestamp":1767638455000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10908400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":46,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3546634","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}