{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:12Z","timestamp":1777865352203,"version":"3.51.4"},"reference-count":70,"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\/iccv51701.2025.01167","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12559-12569","source":"Crossref","is-referenced-by-count":0,"title":["SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation"],"prefix":"10.1109","author":[{"given":"Shiqi","family":"Huang","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuting","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai University of Finance and Economics,MoE Key Laboratory of Interdisciplinary Research of Computation and Economics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaiyuan","family":"Qin","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (IR), A*STAR,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bihan","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Open-vocabulary remote sensing image semantic segmentation","author":"Cao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.103717"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/rs13010039"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356074"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00111"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2014.10.002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3005403"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117983"},{"key":"ref12","first-page":"8090","article-title":"Open-vocabulary universal image segmentation with maskclip","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Ding","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0724"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref15","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/rs14133159"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/rs16162930"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32388"},{"key":"ref19","author":"Ilharco","year":"2021","journal-title":"Openclip"},{"key":"ref20","volume-title":"ISPRS. 2d semantic labeling potsdam dataset","year":"2024"},{"key":"ref21","first-page":"49044916","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_23"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref24","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00986"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.08.001"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3023124"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3022410"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3336563"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00213"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref36","article-title":"Dual local-global contextual pathways for recognition in aerial imagery","author":"Marcu","year":"2016","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3191"},{"key":"ref38","first-page":"arXiv","article-title":"H2rsvlm: Towards helpful and honest remote sensing large vision language model","author":"Pang","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref40","first-page":"87488763","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3090981"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophoto.2022.100024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8898573"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/rs12060989"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883112"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.004"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0385"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01139"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28393"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3188677"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3390\/rs12182910"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/rs13234779"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2523563"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3389\/fmars.2023.1113669"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121007"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1399"},{"key":"ref64","author":"Waqas Zamir","year":"2019","journal-title":"isaid: A large-scale dataset for instance segmentation in aerial images"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00100"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3096185"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030417"},{"issue":"3","key":"ref68","article-title":"Rs5m: A large scale vision-language dataset for remote sensing vision-language foundation model","volume":"2","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.3390\/rs15030549"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3454333"}],"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\/11445153.pdf?arnumber=11445153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:21Z","timestamp":1777529961000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01167","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}