{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T15:05:43Z","timestamp":1776092743203,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB3903404"],"award-info":[{"award-number":["2022YFB3903404"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371140"],"award-info":[{"award-number":["62371140"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2025.3526247","type":"journal-article","created":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T19:31:12Z","timestamp":1736191872000},"page":"1-15","source":"Crossref","is-referenced-by-count":6,"title":["DF<sup>2<\/sup>RQ: Dynamic Feature Fusion via Region-Wise Queries for Semantic Segmentation of Multimodal Remote Sensing Data"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6675-2948","authenticated-orcid":false,"given":"Shiyang","family":"Feng","sequence":"first","affiliation":[{"name":"Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai, China"}]},{"given":"Zhaowei","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8052-782X","authenticated-orcid":false,"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4748-6426","authenticated-orcid":false,"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2020.111838"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2020.111716"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2021.112577"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref6","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/rs11161922"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3302024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.34133\/remotesensing.0078"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113856"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5194\/isprsannals-i-3-293-2012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3016820"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3068532"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3029841"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2895697"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2011.2128330"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078518"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/rs15051454"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2958858"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi10030144"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3017414"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3130716"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3284671"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2017.11.011"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.104042"},{"key":"ref28","first-page":"9226","article-title":"Modality competition: What makes joint training of multi-modal network fail in deep learning? (Provably)","volume-title":"Proc. 39th Int. Conf. Mach. Learn., PMLR, Jun.","author":"Huang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WHISPERS61460.2023.10430584"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WHISPERS61460.2023.10431324"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WHISPERS61460.2023.10431036"},{"key":"ref32","first-page":"10944","article-title":"What makes multi-modal learning better than single (Provably)","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Curran Associates, Inc.","author":"Huang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref35","article-title":"OCNet: Object context network for scene parsing","author":"Yuan","year":"2018","journal-title":"arXiv:1809.00916"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref37","article-title":"PointRend: Image segmentation as rendering","author":"Kirillov","year":"2019","journal-title":"arXiv:1912.08193"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144165"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296757"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3121471"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-annals-v-2-2020-475-2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3414293"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3443420"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1080\/15481603.2024.2356355"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3107672"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref50","article-title":"DeepInteraction: 3D object detection via modality interaction","author":"Yang","year":"2022","journal-title":"arXiv:2208.11112"},{"key":"ref51","article-title":"Meta-transformer: A unified framework for multimodal learning","author":"Zhang","year":"2023","journal-title":"arXiv:2307.10802"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01479"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref55","article-title":"ChartX & ChartVLM: A versatile benchmark and foundation model for complicated chart reasoning","author":"Xia","year":"2024","journal-title":"arXiv:2402.12185"},{"key":"ref56","article-title":"StructChart: On the schema, metric, and augmentation for visual chart understanding","author":"Xia","year":"2023","journal-title":"arXiv:2309.11268"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3401576"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.007"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.09.005"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3165005"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3245324"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3373033"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref65","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Int. Conf. Learn. Represent","author":"Zhu"},{"key":"ref66","article-title":"Fully convolutional networks for dense semantic labelling of high-resolution aerial imagery","author":"Sherrah","year":"2016","journal-title":"arXiv:1606.02585"},{"key":"ref67","article-title":"FastFCN: Rethinking dilated convolution in the backbone for semantic segmentation","author":"Wu","year":"2019","journal-title":"arXiv:1903.11816"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00780"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2988928"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.102896"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10829634.pdf?arnumber=10829634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T06:29:58Z","timestamp":1737440998000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10829634\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3526247","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}