{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:20:20Z","timestamp":1765520420842,"version":"3.48.0"},"reference-count":28,"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\/iros60139.2025.11247182","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"634-641","source":"Crossref","is-referenced-by-count":0,"title":["OpenFusion++: An Open-vocabulary Real-time Scene Understanding System"],"prefix":"10.1109","author":[{"given":"Xiaofeng","family":"Jin","sequence":"first","affiliation":[{"name":"Politecnico di Milano,Milan,Italy,20133"}]},{"given":"Matteo","family":"Frosi","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Milan,Italy,20133"}]},{"given":"Matteo","family":"Matteucci","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Milan,Italy,20133"}]}],"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\/wacv61041.2025.00188"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610193"},{"key":"ref5","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"article-title":"Dinov2: Learning robust visual features without supervision","year":"2023","author":"Oquab","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref10","first-page":"23 033","article-title":"Segclip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"International Conference on Machine Learning","author":"Luo"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"article-title":"Openmask3d: Open-vocabulary 3d instance segmentation","year":"2023","author":"Takmaz","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127896"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_10"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"article-title":"Sam3d: Segment anything in 3d scenes","year":"2023","author":"Yang","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02671"},{"article-title":"Embod-iedsam: Online segment any 3d thing in real time","year":"2024","author":"Xu","key":"ref19"},{"article-title":"Fast segment anything","year":"2023","author":"Zhao","key":"ref20"},{"article-title":"Panoslam: Panoptic 3d scene reconstruction via gaussian slam","year":"2024","author":"Chen","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"article-title":"Ovo-slam: Open-vocabulary online simultaneous localization and mapping","year":"2024","author":"Martins","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907054"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"article-title":"The replica dataset: A digital replica of indoor spaces","year":"2019","author":"Straub","key":"ref28"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247182.pdf?arnumber=11247182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:15:27Z","timestamp":1765520127000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247182","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}