{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:02:58Z","timestamp":1780639378779,"version":"3.54.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ23014"],"award-info":[{"award-number":["JQ23014"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271074"],"award-info":[{"award-number":["62271074"]}],"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":["62302052"],"award-info":[{"award-number":["62302052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education","award":["2024PY021"],"award-info":[{"award-number":["2024PY021"]}]},{"name":"Taishan Scholars Program","award":["TSQN202507241"],"award-info":[{"award-number":["TSQN202507241"]}]},{"name":"Shandong Provincial Key R&D Program","award":["2025KJHZ013"],"award-info":[{"award-number":["2025KJHZ013"]}]},{"name":"National Key R&D Program of China","award":["2025YFE0216800"],"award-info":[{"award-number":["2025YFE0216800"]}]},{"name":"Shandong Provincial University Youth Innovation and Technology Support Program","award":["2022KJ291"],"award-info":[{"award-number":["2022KJ291"]}]},{"name":"Shandong Provincial Natural Science Foundation for Young Scholars Program","award":["ZR2025QC1627"],"award-info":[{"award-number":["ZR2025QC1627"]}]},{"DOI":"10.13039\/501100014890","name":"Qilu University of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014890","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008118","name":"Shandong Academy of Sciences","doi-asserted-by":"publisher","award":["2024QZJH02"],"award-info":[{"award-number":["2024QZJH02"]}],"id":[{"id":"10.13039\/501100008118","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3654453","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T20:50:41Z","timestamp":1768596641000},"page":"3921-3931","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive in Adapter: Boosting Open-Vocabulary Semantic Segmentation With Adaptive Dropout Adapter"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8259-7717","authenticated-orcid":false,"given":"Changwei","family":"Wang","sequence":"first","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Ministry of Education, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4619-9679","authenticated-orcid":false,"given":"Rongtao","family":"Xu","sequence":"additional","affiliation":[{"name":"Spatialtemporal AI, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0377-4023","authenticated-orcid":false,"given":"Zherui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4037-9900","authenticated-orcid":false,"given":"Shibiao","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiguang","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqiang","family":"Teng","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3221-4981","authenticated-orcid":false,"given":"Weiliang","family":"Meng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0092-6474","authenticated-orcid":false,"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3151145"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3270637"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3025696"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3378465"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3406066"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3329870"},{"key":"ref7","first-page":"4326","article-title":"Exploiting multi-label correlation in label distribution learning","volume-title":"Proc. 33rd Int. Joint Conf. Artif. Intell.","author":"Kou","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3311646"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3237166"},{"key":"ref11","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":"ref12","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref14","first-page":"8090","article-title":"Open-vocabulary panoptic segmentation with MaskCLIP","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Ding","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref16","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional CLIP","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yu","year":"2023"},{"key":"ref17","article-title":"Clip surgery for better explainability with enhancement in open-vocabulary tasks","volume":"162","author":"Li","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref18","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume-title":"J. Mach. Learn. Res.","volume":"15","author":"Srivastava","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3333206"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2985708"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311447"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.279"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3380259"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3292597"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3265842"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref35","first-page":"1","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Chen","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00175"},{"key":"ref37","first-page":"1","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00361"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"issue":"1","key":"ref44","first-page":"817","article-title":"Parameter-efficient fine-tuning for vision transformers","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"37","author":"He","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01092"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053605"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref50","first-page":"23033","article-title":"SegClip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Luo","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00116"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00367"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref56","first-page":"1","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3330102"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01251"},{"key":"ref62","first-page":"13548","article-title":"Zero-shot image segmentation via recursive normalized cut on diffusion features","volume-title":"Proc. 38th Int. Conf. Neural Inf. Process. Syst.","author":"Couairon","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0290"},{"key":"ref64","first-page":"25278","article-title":"LAIOn-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Schuhmann","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11353925.pdf?arnumber=11353925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:22:27Z","timestamp":1780636947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3654453","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}