{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T17:34:57Z","timestamp":1772127297619,"version":"3.50.1"},"reference-count":48,"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":[{"name":"Shenzhen Science and Technology Program","award":["JCYJ20210324115604012"],"award-info":[{"award-number":["JCYJ20210324115604012"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20220818103006012"],"award-info":[{"award-number":["JCYJ20220818103006012"]}]},{"name":"Shenzhen Science and Technology Program","award":["KJZD20230923114810022"],"award-info":[{"award-number":["KJZD20230923114810022"]}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20220606100601002"],"award-info":[{"award-number":["ZDSYS20220606100601002"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2021B1515120008"],"award-info":[{"award-number":["2021B1515120008"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515011347"],"award-info":[{"award-number":["2023A1515011347"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Project of General Administration of Customs of the People\u2019s Republic of China","award":["2023HK072"],"award-info":[{"award-number":["2023HK072"]}]},{"name":"Maxvision-AIRS-CUHK(SZ) Joint Laboratory of Inspection Robots"},{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society"}],"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.2024.3378000","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T20:24:07Z","timestamp":1710793447000},"page":"2951-2962","source":"Crossref","is-referenced-by-count":2,"title":["ClickAdapter: Integrating Details Into Interactive Segmentation Model With Adapter"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4869-5174","authenticated-orcid":false,"given":"Shanghong","family":"Li","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, 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 Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7801-4627","authenticated-orcid":false,"given":"Long","family":"Xu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, 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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7950-1662","authenticated-orcid":false,"given":"Rui","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-0509","authenticated-orcid":false,"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingliang","family":"Miao","sequence":"additional","affiliation":[{"name":"Maxvision Technology Corporation, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00136"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00180"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00865"},{"key":"ref4","article-title":"SimpleClick: Interactive image segmentation with simple vision transformers","author":"Liu","year":"2022","journal-title":"arXiv:2210.11006"},{"key":"ref5","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref9","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv:2205.08534"},{"key":"ref10","article-title":"What do vision transformers learn? A visual exploration","author":"Ghiasi","year":"2022","journal-title":"arXiv:2212.06727"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.233"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540073"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540078"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015720"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.47"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01335"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00544"},{"key":"ref18","article-title":"Getting to 99% accuracy in interactive segmentation","author":"Forte","year":"2020","journal-title":"arXiv:2003.07932"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897365"},{"key":"ref20","article-title":"Cascaded sparse feature propagation network for interactive segmentation","author":"Zhang","year":"2022","journal-title":"arXiv:2203.05145"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie"},{"key":"ref24","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref26","first-page":"5986","article-title":"BERT and pals: Projected attention layers for efficient adaptation in multi-task learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stickland"},{"key":"ref27","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2884462"},{"key":"ref29","first-page":"1","article-title":"Learning multiple visual domains with residual adapters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Rebuffi"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref32","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2009.03.008"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref39","first-page":"1","article-title":"Segment anything in high quality","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00431"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00725"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937505"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00035"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_3"},{"key":"ref47","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00733"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10949577\/10473126.pdf?arnumber=10473126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T22:13:19Z","timestamp":1744063999000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10473126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":48,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3378000","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}