{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:37Z","timestamp":1778048377813,"version":"3.51.4"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00589","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6090-6100","source":"Crossref","is-referenced-by-count":0,"title":["MUSE: Model-based Uncertainty-aware Similarity Estimation for zero-shot 2D Object Detection and Segmentation"],"prefix":"10.1109","author":[{"given":"Sungmin","family":"Cho","sequence":"first","affiliation":[{"name":"Netmarble"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungbum","family":"Park","sequence":"additional","affiliation":[{"name":"Netmarble"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Insoo","family":"Oh","sequence":"additional","affiliation":[{"name":"Netmarble"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization","volume":"2","author":"Bai","year":"2023","journal-title":"Text Reading, and Beyond"},{"key":"ref2","article-title":"Introducing hot3d: An egocentric dataset for 3d hand and object tracking","author":"Banerjee","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/45.3-4.296"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-00e"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","article-title":"Zeropose: Cad-model-based zeroshot pose estimation","author":"Chen","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.390"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.257"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341672"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.103"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00570"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00570"},{"key":"ref15","article-title":"Xyz-ibd: High-precision bin-picking dataset for object 6d pose estimation capturing real-world industrial complexity","author":"Huang","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02141"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2795645"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00338"},{"key":"ref19","article-title":"Segment anything in high quality","volume":"36","author":"Ke","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02636"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3244348"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlastec.2025.114078"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11245990"},{"key":"ref28","article-title":"Advancing 6d pose estimation in augmented reality\u2013 overcoming projection ambiguity with uncontrolled imagery","author":"Manawadu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2513408"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00665"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00227"},{"key":"ref32","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CASE56687.2023.10260335"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref36","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref37","article-title":"Dinov3","author":"Sim\u00e9oni","year":"2025"},{"key":"ref38","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00279"},{"key":"ref40","first-page":"1957","article-title":"Ibm internal report","volume":"17","author":"Tanimoto","year":"1957","journal-title":"Nov"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981838"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811568"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref46","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97909-0_37"},{"key":"ref48","article-title":"Fast segment anything","author":"Zhao","year":"2023"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492453.pdf?arnumber=11492453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:48Z","timestamp":1778047008000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00589","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}