{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:53:32Z","timestamp":1783738412932,"version":"3.55.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02290","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24698-24706","source":"Crossref","is-referenced-by-count":2,"title":["Online Reasoning Video Segmentation with Just-in-Time Digital Twins"],"prefix":"10.1109","author":[{"given":"Yiqing","family":"Shen","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Baltimore,MD,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bohan","family":"Liu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,MD,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenjia","family":"Li","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,MD,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lalithkumar","family":"Seenivasan","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,MD,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathias","family":"Unberath","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,MD,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_11"},{"key":"ref2","author":"Darvishi-Bayazi","year":"2024","journal-title":"Vfa: Vision frequency analysis of foundation models and human"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref4","author":"Ding","year":"2024","journal-title":"Towards robust automation of surgical systems via digital twin-based scene representations from foundation models"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-07694-6_12"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13646"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.09.116"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00553"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirpj.2020.02.002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.249"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref15","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"How can large language models understand spatial-temporal data? arXiv preprint arXiv:2401","author":"Liu","year":"2024","journal-title":"4192"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref18","article-title":"Scaling open-vocabulary object detection","author":"Minderer","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462870"},{"key":"ref20","first-page":"792","article-title":"Modeling context between objects for referring expression understanding","volume-title":"Computer Vision-ECCV 2016: 14th European Conference","author":"Varun","year":"2016"},{"key":"ref21","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref23","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref24","author":"Stroh","year":"2024","journal-title":"Trackgpt-a generative pre-trained transformer for cross-domain entity trajectory forecasting"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00183"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01243"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref28","author":"Xu","year":"2024","journal-title":"A survey on robotics with foundation models: toward embodied ai"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444173.pdf?arnumber=11444173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:03Z","timestamp":1777613343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02290","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}