{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:31:36Z","timestamp":1784737896578,"version":"3.55.0"},"reference-count":38,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lsp.2026.3663047","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:11:33Z","timestamp":1770671493000},"page":"943-947","source":"Crossref","is-referenced-by-count":1,"title":["MFT: Memory-Aware Fine-Tuning of SAM2 for Efficient Long-Sequence Video Object Segmentation"],"prefix":"10.1109","volume":"33","author":[{"given":"Guoqiang","family":"Li","sequence":"first","affiliation":[{"name":"National Science Library, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Moffett Field, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The City College of New York, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Hu","sequence":"additional","affiliation":[{"name":"Khoury College of Computer Sciences, Northeastern University, Vancouver, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"Economics and Management School, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3688-965X","authenticated-orcid":false,"given":"Kunming","family":"Jiang","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00774"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.790"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00940"},{"key":"ref7","article-title":"MaskRNN: Instance level video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Hu","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00147"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref10","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3059195"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3066071"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3625880"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref15","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":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref20","article-title":"Decoupling features in hierarchical propagation for video object segmentation","author":"Yang","year":"2022"},{"key":"ref21","article-title":"Joint modeling of feature, correspondence, and a compressed memory for video object segmentation","author":"Zhang","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref24","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref25","article-title":"Partial fine-tuning: A successor to full fine-tuning for vision transformers","author":"Ye","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref27","first-page":"29441","article-title":"Hiera: A hierarchical vision transformer without the Bells-and-Whistles","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ryali","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref31","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3611020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00139"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01276"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00225"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/11304147\/11386858.pdf?arnumber=11386858","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T07:01:02Z","timestamp":1772089262000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11386858\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/lsp.2026.3663047","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}