{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T13:46:56Z","timestamp":1780926416869,"version":"3.54.1"},"reference-count":58,"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\/iccv51701.2025.02085","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22457-22466","source":"Crossref","is-referenced-by-count":5,"title":["Dynamic Dictionary Learning for Remote Sensing Image Segmentation"],"prefix":"10.1109","author":[{"given":"Xuechao","family":"Zou","sequence":"first","affiliation":[{"name":"School of Computer Science & Technology, Beijing Jiaotong University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Technology and Application, Qinghai University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Technology and Application, Qinghai University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiying","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Technology and Application, Qinghai University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pin","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Computer Technology and Application, Qinghai University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congyan","family":"Lang","sequence":"additional","affiliation":[{"name":"School of Computer Science & Technology, Beijing Jiaotong University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01878-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.01.026"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103280"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3444773"},{"key":"ref7","first-page":"17864","article-title":"Perpixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref9","first-page":"6591","article-title":"Learning dynamic query combinations for transformer-based object detection and segmentation","volume-title":"ICML","author":"Cui","year":"2023"},{"key":"ref10","first-page":"2988","article-title":"Dynamic detr: End-toend object detection with dynamic attention","volume-title":"ICCV","author":"Dai","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/rs13204100"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.103820"},{"key":"ref13","first-page":"1","article-title":"Kolesnikov. An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"I C L R","author":"Dosovitskiy","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2017.03.026"},{"key":"ref15","volume-title":"International Society for Photogrammetry and Remote Sensing. Posdam datasets","year":"2024"},{"key":"ref16","volume-title":"International Society for Photogrammetry and Remote Sensing. Vaihingen datasets","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3321716"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2991398"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/rs16162930"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.06.003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/rs16173278"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.33.4.043027"},{"key":"ref27","first-page":"1","article-title":"An efficient encoder-decoder architecture with top-down attention for speech separation","volume-title":"I C L R","author":"Li","year":"2023"},{"key":"ref28","article-title":"Iianet: an intra- and inter-modality attention network for audiovisual speech separation","volume-title":"ICML. JMLR.org","author":"Li","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.09.005"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref33","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3175613"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.05.009"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32661"},{"key":"ref38","first-page":"1","article-title":"Moutakanni. DINOv2: Learning Robust Visual Features without Supervision","volume-title":"TMLR","author":"Oquab","year":"2024"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","first-page":"1","article-title":"LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation","volume-title":"NeurIPS","author":"Wang","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/rs13163065"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref49","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume-title":"NeurIPS","author":"Xie","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2904868"},{"key":"ref51","article-title":"Segvit: Semantic segmentation with plain vision transformers","volume-title":"NeurIPS","author":"Zhang","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01894-8"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11209838"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i20.30260"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230636"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3365806"}],"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\/11445326.pdf?arnumber=11445326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:30:46Z","timestamp":1777530646000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02085","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}