{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T05:04:21Z","timestamp":1783487061105,"version":"3.55.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["62572072"],"award-info":[{"award-number":["62572072"]}],"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":["U24B20176"],"award-info":[{"award-number":["U24B20176"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L243027"],"award-info":[{"award-number":["L243027"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tpami.2025.3646919","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:41:22Z","timestamp":1766428882000},"page":"4642-4656","source":"Crossref","is-referenced-by-count":3,"title":["DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6955-6635","authenticated-orcid":false,"given":"Mengshi","family":"Qi","sequence":"first","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0550-8247","authenticated-orcid":false,"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3241-5821","authenticated-orcid":false,"given":"Xiaoyang","family":"Bi","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Qi","sequence":"additional","affiliation":[{"name":"University of California Merced, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7199-5047","authenticated-orcid":false,"given":"Huadong","family":"Ma","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-2304","authenticated-orcid":false,"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California Merced, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref2","first-page":"41175","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref4","first-page":"21429","article-title":"Hierarchical open-vocabulary universal image segmentation","volume":"36","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3562930"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"ref8","article-title":"Sa2Va: Marrying sam2 with llava for dense grounded understanding of images and videos","author":"Yuan","year":"2025"},{"key":"ref9","article-title":"Generalizable entity grounding via assistance of large language model","author":"Qi","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013717"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00789"},{"key":"ref14","first-page":"21984","article-title":"Few-shot segmentation via cycle-consistent transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.,","volume":"34","author":"Zhang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02264"},{"key":"ref16","first-page":"31524","article-title":"Focus on query: Adversarial mining transformer for few-shot segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00324"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"ref21","first-page":"42382","article-title":"Explore in-context learning for 3D point cloud understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Fang","year":"2023"},{"key":"ref22","first-page":"13754","article-title":"Personalize segment anything model with one shot","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2024"},{"key":"ref23","first-page":"4986","article-title":"Matcher: Segment anything with one shot using all-purpose feature matching","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02224"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref26","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01240"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3611020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref31","article-title":"Segment and track anything","author":"Cheng","year":"2023"},{"key":"ref32","article-title":"EdgeSAM: Prompt-in-the-loop distillation for on-device deployment of SAM","author":"Zhou","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00273"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103310"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0546"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2983567"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00408"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2894161"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_14"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680609"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00310"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00919"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00124"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3421340"},{"key":"ref46","article-title":"Towards generalized and incremental few-shot object detection","author":"Li","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00823"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.167"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3627224"},{"key":"ref50","first-page":"30816","article-title":"Universal few-shot learning of dense prediction tasks with visual token matching","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3613952"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1813"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","article-title":"DINOV2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref55","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01188"},{"key":"ref57","first-page":"445","article-title":"A benchmark and simulator for UAV tracking","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Benchmark","year":"2016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref59","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00071"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref63","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","volume":"32","author":"Paszke","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref65","first-page":"4061","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref66","first-page":"6941","article-title":"Hypercorrelation squeeze for few-shot segmentation","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Min","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_41"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01128"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01126"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1093\/beheco\/ark016"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00348"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3172773"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.5566\/ias.2346"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_45"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01376"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_29"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_13"},{"key":"ref79","first-page":"6575","article-title":"Feature-proxy transformer for few-shot segmentation","volume-title":"Proc. NeurIPS","author":"Zhang","year":"2022"},{"key":"ref80","first-page":"12513","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11424231\/11311151.pdf?arnumber=11311151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:34:43Z","timestamp":1773106483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11311151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":80,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3646919","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}