{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:33:23Z","timestamp":1763192003613,"version":"3.45.0"},"reference-count":36,"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\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009013","name":"Jimei University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009013","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\/ijcnn64981.2025.11229175","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["MarIns3D: A Open Vocabulary 3D Instance Segmentation Model with Mask Refinement"],"prefix":"10.1109","author":[{"given":"Haiyang","family":"Li","sequence":"first","affiliation":[{"name":"JiMei University,The College of Computer Engineering,Xiamen,China,361021"}]},{"given":"Mengyun","family":"Cao","sequence":"additional","affiliation":[{"name":"JiMei University,The College of Computer Engineering,Xiamen,China,361021"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00317"},{"key":"ref4","article-title":"Open-yolo 3d: Towards fast and accurate open-vocabulary 3d instance segmentation","author":"Boudjoghra","year":"2024","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_10"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01874"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref9","article-title":"Segment any 3d object with language","author":"Lee","year":"2024","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00455"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3363054"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_4"},{"article-title":"3d-queryis: A query-based framework for 3d instance segmentation","year":"2022","author":"Liu","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00042"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_14"},{"key":"ref18","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.04.019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"article-title":"Open-vocabulary segmentation with unpaired mask-text supervision","year":"2024","author":"Wang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref27","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","volume":"36","author":"Yu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"ref32","first-page":"1610","article-title":"Ovir-3d: Open-vocabulary 3d instance retrieval without training on 3d data","volume-title":"Conference on Robot Learning","author":"Lu"},{"article-title":"Sam3d: Segment anything in 3d scenes","year":"2023","author":"Yang","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3410324"},{"key":"ref36","first-page":"68367","article-title":"Openmask3d: open-vocabulary 3d instance segmentation","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Takmaz"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229175.pdf?arnumber=11229175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:29:59Z","timestamp":1763191799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229175\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229175","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}