{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:32:54Z","timestamp":1772829174170,"version":"3.50.1"},"reference-count":48,"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"}],"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"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011311","name":"State Key Laboratory of Industrial Control Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247337","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"2193-2200","source":"Crossref","is-referenced-by-count":2,"title":["Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance"],"prefix":"10.1109","author":[{"given":"Jiayi","family":"Zhao","sequence":"first","affiliation":[{"name":"Hunan University,School of Artificial Intelligence and Robotics,China"}]},{"given":"Fei","family":"Teng","sequence":"additional","affiliation":[{"name":"Hunan University,School of Artificial Intelligence and Robotics,China"}]},{"given":"Kai","family":"Luo","sequence":"additional","affiliation":[{"name":"Hunan University,School of Artificial Intelligence and Robotics,China"}]},{"given":"Guoqiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Hunan University,School of Artificial Intelligence and Robotics,China"}]},{"given":"Zhiyong","family":"Li","sequence":"additional","affiliation":[{"name":"Hunan University,School of Artificial Intelligence and Robotics,China"}]},{"given":"Xu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,AI Thrust,Guangzhou,China"}]},{"given":"Kailun","family":"Yang","sequence":"additional","affiliation":[{"name":"Hunan University,School of Artificial Intelligence and Robotics,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref2","first-page":"12 077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. NeurIPS","volume":"34","author":"Xie"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref7","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611127"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3443420"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687602"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103547"},{"key":"ref12","first-page":"3359","article-title":"SAM-adapter: Adapting segment anything in under-performed scenes","volume-title":"Proc. ICCVW","author":"Chen"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref15","article-title":"GeminiFusion: Efficient pixel-wise multimodal fusion for vision transformer","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref17","first-page":"1071","article-title":"Simple and efficient vision backbone adapter for image semantic segmentation","volume-title":"Proc. ACML","author":"Peng"},{"key":"ref18","article-title":"LanguageBind: Extending video-language pretraining to N-modality by language-based semantic alignment","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636084"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2024.3389812"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3306368"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02687-7"},{"key":"ref25","article-title":"HAPNet: Toward superior RGB-thermal scene parsing via hybrid, asymmetric, and progressive heterogeneous feature fusion","author":"Li","year":"2024"},{"key":"ref26","article-title":"Segment anything with multiple modalities","author":"Xiao","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_9"},{"key":"ref34","first-page":"29 441","article-title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","volume-title":"Proc. ICML","volume":"202","author":"Ryali"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref37","article-title":"Language-driven semantic segmentation","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3314527"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801872"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611200"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_24"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208833"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/135"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3012548"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111801"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"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\/11247337.pdf?arnumber=11247337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:16:13Z","timestamp":1765520173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247337","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}