{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:30:21Z","timestamp":1791567021615,"version":"4.3.4"},"reference-count":63,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3651835","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:01:14Z","timestamp":1768338074000},"page":"970-982","source":"Crossref","is-referenced-by-count":9,"title":["SAMURAI: Motion-Aware Memory for Training-Free Visual Object Tracking With SAM 2"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2631-6756","authenticated-orcid":false,"given":"Cheng-Yen","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2474-8869","authenticated-orcid":false,"given":"Hsiang-Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2611-0008","authenticated-orcid":false,"given":"Wenhao","family":"Chai","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4462-6497","authenticated-orcid":false,"given":"Zhongyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8877-2421","authenticated-orcid":false,"given":"Jenq-Neng","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref2","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.128"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_39"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25085-9_25"},{"key":"ref12","first-page":"777","article-title":"The visual object tracking VOT2016 challenge results","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","volume":"9914","author":"Hadfield"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00472"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00441"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01802"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref23","article-title":"AuroraCap: Efficient, performant video detailed captioning and a new benchmark","author":"Chai","year":"2024","journal-title":"arXiv:2410.03051"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref25","article-title":"MovieChat+: Question-aware sparse memory for long video question answering","author":"Song","year":"2024","journal-title":"arXiv:2404.17176"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref29","article-title":"Fast segment anything","author":"Zhao","year":"2023","journal-title":"arXiv:2306.12156"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A new approach to linear filtering and prediction problems","volume":"82","author":"Ding","year":"1960","journal-title":"J. Basic Eng."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02259"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"issue":"46","key":"ref33","first-page":"3736","article-title":"Kalman and extended Kalman filters: Concept, derivation and properties","volume":"43","author":"Ribeiro","year":"2004","journal-title":"Inst. Syst. Robot."},{"key":"ref34","article-title":"BoT-SORT: Robust associations multi-pedestrian tracking","author":"Aharon","year":"2022","journal-title":"arXiv:2206.14651"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106539"},{"key":"ref36","article-title":"MambaMOT: State-space model as motion predictor for multi-object tracking","author":"Huang","year":"2024","journal-title":"arXiv:2403.10826"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref39","first-page":"29441","article-title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ryali"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"ref45","first-page":"16743","article-title":"SwinTrack: A simple and strong baseline for transformer tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00668"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28286"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01822"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_17"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3349519"},{"key":"ref57","article-title":"Associating objects with transformers for video object segmentation","author":"Yang","year":"2021","journal-title":"arXiv:2106.02638"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3453028"},{"key":"ref61","first-page":"11781","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2632"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11351313.pdf?arnumber=11351313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T04:19:26Z","timestamp":1775881166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11351313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3651835","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}