{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:09:48Z","timestamp":1761894588144,"version":"build-2065373602"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209420","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["SAM2-Cap: Segment Anything 2 with using Parts and Object Spatial Hierarchical Relationships for Image Segmentation"],"prefix":"10.1109","author":[{"given":"Xiufeng","family":"Liu","sequence":"first","affiliation":[{"name":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongqiu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghui","family":"Hu","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0734-189X(85)90153-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"Sam 2: Segment anything in images and videos","year":"2024","author":"Ravi","key":"ref8"},{"article-title":"Dynamic routing between capsules","year":"2017","author":"Sabour","key":"ref9"},{"article-title":"Matrix capsules with em routing","volume-title":"International conference on learning representations","author":"Hinton","key":"ref10"},{"key":"ref11","article-title":"Stacked capsule autoencoders","volume":"32","author":"Kosiorek","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"9213","article-title":"Unsupervised part representation by flow capsules","volume-title":"International Conference on Machine Learning","author":"Sabour"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0303_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.09.010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687368"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00011"},{"key":"ref17","article-title":"The infinite gaussian mixture model","volume":"12","author":"Rasmussen","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59713-9_46"},{"issue":"6","key":"ref21","first-page":"5","article-title":"Nci-isbi 2013 challenge: automated segmentation of prostate structures","volume":"370","author":"Bloch","year":"2015","journal-title":"The Cancer Imaging Archive"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2015.02.009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2013.12.002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_15"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/4037190"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2487997"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-013-0926-3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59710-8_65"},{"article-title":"Robust and generalizable visual representation learning via random convolutions","year":"2020","author":"Xu","key":"ref30"},{"article-title":"Domain generalization with mixstyle","year":"2021","author":"Zhou","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3224067"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_66"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1117\/12.2611802"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109555"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00533"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00939"},{"article-title":"Rethinking atrous convolution for semantic image segmentation","year":"2017","author":"Chen","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01188-y"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.15203"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvmi61877.2024.10782648"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209420.pdf?arnumber=11209420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:31:28Z","timestamp":1761888688000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209420","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}