{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T22:39:19Z","timestamp":1769035159959,"version":"3.49.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339342","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["MMMS: Multi-Modal Multi-Surface Interactive Segmentation"],"prefix":"10.1109","author":[{"given":"Robin","family":"Sch\u00f6n","sequence":"first","affiliation":[{"name":"Fakultät für Angewandte Informatik, University of Augsburg,Augsburg,Germany"}]},{"given":"Julian","family":"Lorenz","sequence":"additional","affiliation":[{"name":"Fakultät für Angewandte Informatik, University of Augsburg,Augsburg,Germany"}]},{"given":"Katja","family":"Ludwig","sequence":"additional","affiliation":[{"name":"Fakultät für Angewandte Informatik, University of Augsburg,Augsburg,Germany"}]},{"given":"Daniel","family":"Kienle","sequence":"additional","affiliation":[{"name":"Fakultät für Angewandte Informatik, University of Augsburg,Augsburg,Germany"}]},{"given":"Rainer","family":"Lienhart","sequence":"additional","affiliation":[{"name":"Fakultät für Angewandte Informatik, University of Augsburg,Augsburg,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref2","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021","journal-title":"Neural Information Pro-cessing Systems (Ne u rIPS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR62202.2024.00019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897365"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00136"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.7557\/18.6823"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01225"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00865"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02037"},{"key":"ref11","first-page":"36","article-title":"Segment anything in high quality","author":"Ke","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02038"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00362"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00138"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01189"},{"key":"ref16","article-title":"Efficient full image interactive segmentation by leveraging within-image appearance similarity","author":"Andriluka","year":"2020","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00102"},{"key":"ref18","article-title":"Learning from exemplars for interactive image segmentation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2904733"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01918"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422432"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3536218"},{"key":"ref29","first-page":"21753","article-title":"GeminiFusion: Efficient pixel-wise multimodal fusion for vision transformer","volume-title":"Ruslan Salakhutdinov","author":"Jia"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755110"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00509"},{"key":"ref32","author":"Wang","year":"2025","journal-title":"Order-aware interactive segmentation"},{"key":"ref33","first-page":"1","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research Journal"},{"key":"ref34","author":"Darcet","year":"2023","journal-title":"Vision transformers need registers"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01499"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015720"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2009.03.008"},{"key":"ref44","author":"Huang","year":"2024","journal-title":"Hrsam: Efficient interactive segmentation in high-resolution images"},{"key":"ref45","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339342.pdf?arnumber=11339342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:11:39Z","timestamp":1768979499000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339342","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}