{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T11:19:54Z","timestamp":1775042394238,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128804","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"11155-11161","source":"Crossref","is-referenced-by-count":2,"title":["VideoSAM: Open-World Video Segmentation"],"prefix":"10.1109","author":[{"given":"Pinxue","family":"Guo","sequence":"first","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University."}]},{"given":"Zixu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Amazon Web Services Shanghai AI Lab"}]},{"given":"Jianxiong","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Science and Technology for Brain-inspired Intelligence, Fudan University"}]},{"given":"Chongruo","family":"Wu","sequence":"additional","affiliation":[{"name":"Amazon Web Services Shanghai AI Lab"}]},{"given":"Tong","family":"He","sequence":"additional","affiliation":[{"name":"Amazon Web Services Shanghai AI Lab"}]},{"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Amazon Web Services Shanghai AI Lab"}]},{"given":"Tianjun","family":"Xiao","sequence":"additional","affiliation":[{"name":"Amazon Web Services Shanghai AI Lab"}]},{"given":"Wenqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-32-385787-1.00017-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561690"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00317"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3207665"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00049"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3136185"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref8","author":"Cheng","year":"2023","journal-title":"Segment and track anything"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00901"},{"key":"ref10","author":"Yang","year":"2023","journal-title":"Track anything: Segment anything meets videos"},{"key":"ref11","first-page":"36324","article-title":"Decoupling features in hierarchical propagation for video object segmentation","volume":"35","author":"Yang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref15","author":"Dosovitskiy","year":"2020","journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale"},{"key":"ref16","author":"Ranzinger","year":"2023","journal-title":"Am-radio: Agglomerative model-reduce all domains into one"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00172"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611409"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3227513"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref24","author":"Parnami","year":"2022","journal-title":"Learning from few examples: A summary of approaches to few-shot learning"},{"key":"ref25","author":"Hsu","year":"2018","journal-title":"Unsupervised learning via meta-learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01522"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811873"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/app12199408"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01032"},{"key":"ref31","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume":"34","author":"Yang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref33","author":"Sun","year":"2020","journal-title":"Transtrack: Multiple object tracking with transformer"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref36","author":"Zhou","year":"2024","journal-title":"Sam-pd: How far can sam take us in tracking and segmenting anything in videos by prompt denoising"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01794"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611726"},{"key":"ref39","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128804.pdf?arnumber=11128804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:17:43Z","timestamp":1756880263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128804\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128804","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}