{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:13:47Z","timestamp":1777889627157,"version":"3.51.4"},"reference-count":64,"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"}],"funder":[{"DOI":"10.13039\/501100006465","name":"Korea Creative Content Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006465","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003561","name":"Ministry of Culture, Sports and Tourism","doi-asserted-by":"publisher","award":["RS-2024-00345025,RS-2024-00333068"],"award-info":[{"award-number":["RS-2024-00345025,RS-2024-00333068"]}],"id":[{"id":"10.13039\/501100003561","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00346597"],"award-info":[{"award-number":["RS-2024-00346597"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01881","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20226-20236","source":"Crossref","is-referenced-by-count":0,"title":["S\n                    <sup>4<\/sup>\n                    M: Boosting Semi-Supervised Instance Segmentation with SAM"],"prefix":"10.1109","author":[{"given":"Heeji","family":"Yoon","sequence":"first","affiliation":[{"name":"KAIST AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heeseong","family":"Shin","sequence":"additional","affiliation":[{"name":"KAIST AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eunbeen","family":"Hong","sequence":"additional","affiliation":[{"name":"KAIST AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyunwook","family":"Choi","sequence":"additional","affiliation":[{"name":"Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hansang","family":"Cho","sequence":"additional","affiliation":[{"name":"Samsung Electro-Mechanics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daun","family":"Jeong","sequence":"additional","affiliation":[{"name":"Samsung Electro-Mechanics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungryong","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","article-title":"Deep vit features as dense visual descriptors","volume":"2","author":"Amir","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00111"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00053"},{"key":"ref4","article-title":"Segment any anomaly without training via hybrid prompt regularization","author":"Cao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Depth-guided semi-supervised instance segmentation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"17864","article-title":"Perpixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref8","first-page":"9011","article-title":"Cats: Cost aggregation transformers for visual correspondence","volume":"34","author":"Cho","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3218727"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00394"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref12","first-page":"702","article-title":"Randaugment: Practical automated data augmentation with a reduced search space","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops","author":"Ekin","year":"2020"},{"key":"ref13","article-title":"Samaug: Point prompt augmentation for segment anything model","author":"Dai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2010","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3374073"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00067"},{"key":"ref22","author":"Hinton","year":"2015","journal-title":"Distilling the knowledge in a neural network"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00976"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0982"},{"key":"ref26","article-title":"Unifying feature and cost aggregation with transformers for semantic and visual correspondence","author":"Hong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01909"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01497"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103061"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3536481"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01844"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72120-5_16"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00141"},{"key":"ref40","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00433"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00901"},{"key":"ref45","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv preprint"},{"key":"ref48","first-page":"29441","article-title":"Hiera: A hierarchical vision transformer without the bells-andwhistles","volume-title":"International Conference on Machine Learning","author":"Ryali","year":"2023"},{"key":"ref49","first-page":"9153","article-title":"Towards open-vocabulary semantic segmentation without semantic labels","volume":"37","author":"Shin","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume":"33","author":"Sohn","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref51","article-title":"Possam: Panoptic open-vocabulary segment anything","author":"Vibashan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00367"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01632"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01632"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0253"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17785"},{"key":"ref57","article-title":"Track anything: Segment anything meets videos","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref60","article-title":"Personalize segment anything model with one shot","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM62325.2024.10821951"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.79"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102569"}],"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\/11445428.pdf?arnumber=11445428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:15Z","timestamp":1777612455000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445428\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01881","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}