{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:46Z","timestamp":1777888666396,"version":"3.51.4"},"reference-count":56,"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\/iccv51701.2025.02212","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23828-23838","source":"Crossref","is-referenced-by-count":0,"title":["ZIM: Zero-Shot Image Matting for Anything"],"prefix":"10.1109","author":[{"given":"Beomyoung","family":"Kim","sequence":"first","affiliation":[{"name":"NAVER Cloud, ImageVision"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanyong","family":"Shin","sequence":"additional","affiliation":[{"name":"NAVER Cloud, ImageVision"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joonhyun","family":"Jeong","sequence":"additional","affiliation":[{"name":"NAVER Cloud, ImageVision"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyungsik","family":"Jung","sequence":"additional","affiliation":[{"name":"NAVER Cloud, ImageVision"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Se-Yun","family":"Lee","sequence":"additional","affiliation":[{"name":"NAVER Cloud, ImageVision"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sewhan","family":"Chun","sequence":"additional","affiliation":[{"name":"NAVER Cloud, ImageVision"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong-Hyun","family":"Hwang","sequence":"additional","affiliation":[{"name":"NAVER Cloud, ImageVision"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joonsang","family":"Yu","sequence":"additional","affiliation":[{"name":"NAVER Cloud, ImageVision"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30695-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408931"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1130"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240610"},{"key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3155958"},{"key":"ref8","article-title":"An image is worth 16 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","volume-title":"Clipaway: Harmonizing focused embeddings for removing objects via diffusion models","author":"Ekin","year":"2024"},{"key":"ref10","first-page":"423","article-title":"Random walks for interactive alpha-matting","volume-title":"Proceedings of VIIP","author":"Grady","year":"2005"},{"key":"ref11","volume-title":"X-ray images of the hip joints","author":"Gut","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref13","article-title":"Segment anything in high quality","volume":"36","author":"Ke","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19999"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01093"},{"key":"ref16","article-title":"Towards labelefficient human matting: A simple baseline for weakly semi-supervised trimap-free human matting","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00322"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475512"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/111"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01541-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01541-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02150"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00184"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6809"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00035"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00746"},{"key":"ref30","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Loshchilov","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00336"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918"},{"key":"ref33","article-title":"Hasnin, kaggle446, shirzad, Will Cukierski, and yffud","author":"Montoya","year":"2016","journal-title":"Ultrasound nerve segmentation"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01140"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00198"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01369"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_3"},{"key":"ref38","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00604"},{"key":"ref40","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":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897365"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultras.2022.106706"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01097"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00267"},{"key":"ref45","first-page":"33:17721","article-title":"Solov2: Dynamic and fast instance segmentation","author":"Wang","year":"2020","journal-title":"Advances in Neural information processing systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01512"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.41"},{"key":"ref48","article-title":"Unified interactive image matting","author":"Yang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102091"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105067"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02417"},{"key":"ref52","volume-title":"Inst-inpaint: Instructing to remove objects with diffusion models","author":"Yildirim","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00121"},{"key":"ref54","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00733"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"}],"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\/11444964.pdf?arnumber=11444964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:51Z","timestamp":1777611291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02212","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}