{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:30:04Z","timestamp":1773171004261,"version":"3.50.1"},"reference-count":69,"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\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Academic Research Fund Tier 2","award":["MOE-T2EP20124-0012"],"award-info":[{"award-number":["MOE-T2EP20124-0012"]}]}],"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.2025.3648863","type":"journal-article","created":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T18:23:41Z","timestamp":1766773421000},"page":"4878-4895","source":"Crossref","is-referenced-by-count":0,"title":["SAM-I2V++: Efficiently Upgrading SAM for Promptable Video Segmentation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3549-9684","authenticated-orcid":false,"given":"Haiyang","family":"Mei","sequence":"first","affiliation":[{"name":"Show Lab, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Show Lab, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7681-2166","authenticated-orcid":false,"given":"Mike Zheng","family":"Shou","sequence":"additional","affiliation":[{"name":"Show Lab, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-02920-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00065"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00375"},{"key":"ref5","article-title":"SAM2: Segment anything in images and videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i19.34255"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00324"},{"key":"ref8","first-page":"29914","article-title":"Segment anything in high quality","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Ke","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref10","article-title":"Faster segment anything: Towards lightweight SAM for mobile applications","author":"Zhang","year":"2023"},{"key":"ref11","article-title":"MobileSAMv2: Faster segment anything to everything","author":"Zhang","year":"2023"},{"key":"ref12","article-title":"Fast segment anything","author":"Zhao","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1246"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103547"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356074"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00817"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_11"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tbme.2026.3653267"},{"key":"ref21","article-title":"Medical SAM 2: Segment medical images as video via segment anything model 2","author":"Zhu","year":"2024"},{"key":"ref22","article-title":"Interactive 3D medical image segmentation with SAM 2","author":"Shen","year":"2024"},{"key":"ref23","article-title":"Surgical SAM 2: Real-time segment anything in surgical video by efficient frame pruning","author":"Liu","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-025-00106-w"},{"key":"ref25","article-title":"SAM2-Adapter: Evaluating & adapting segment anything 2 in downstream tasks: Camouflage, shadow, medical image segmentation, and more","author":"Chen","year":"2024"},{"key":"ref26","first-page":"13614","article-title":"SAM2LONG: Enhancing SAM 2 for long video segmentation with a training-free memory tree","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Ding","year":"2025"},{"key":"ref27","article-title":"Samurai: Adapting segment anything model for zero-shot visual tracking with motion-aware memory","author":"Yang","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02259"},{"key":"ref29","article-title":"SAMA: Material-aware 3D selection and segmentation","author":"Fischer","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01291"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_18"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00551"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00680"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref35","article-title":"Track Anything: Segment anything meets videos","author":"Yang","year":"2023"},{"key":"ref36","article-title":"Segment and track anything","author":"Cheng","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00901"},{"key":"ref38","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref46","first-page":"11781","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Cheng","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"ref49","article-title":"Joint modeling of feature, correspondence, and a compressed memory for video object segmentation","author":"Zhang","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01276"},{"key":"ref51","first-page":"26462","article-title":"ST-Adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Pan","year":"2022"},{"key":"ref52","article-title":"AIM: Adapting image models for efficient video action recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00219"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01281"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref57","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref58","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007032"},{"key":"ref60","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref61","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref62","article-title":"Electra: Pre-training text encoders as discriminators rather than generators","author":"Clark","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6916"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref65","article-title":"EdgeSAM: Prompt-in-the-loop distillation for on-device deployment of SAM","author":"Zhou","year":"2023"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/ac9b86"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS57966.2023.10168660"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3495769"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3510627"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11424231\/11316399.pdf?arnumber=11316399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:34:58Z","timestamp":1773106498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11316399\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":69,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3648863","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]]}}}