{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T22:49:26Z","timestamp":1778539766512,"version":"3.51.4"},"reference-count":122,"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":"Major Program Project of Xiangjiang Laboratory","award":["22XJ01010"],"award-info":[{"award-number":["22XJ01010"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42271481"],"award-info":[{"award-number":["42271481"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Using Computing Resources at the High-Performance Computing Platform of Central South University","doi-asserted-by":"publisher","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.2025.3526725","type":"journal-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T14:31:30Z","timestamp":1736260290000},"page":"1-20","source":"Crossref","is-referenced-by-count":28,"title":["AllSpark: A Multimodal Spatiotemporal General Intelligence Model With Ten Modalities via Language as a Reference Framework"],"prefix":"10.1109","volume":"63","author":[{"given":"Run","family":"Shao","sequence":"first","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha, China"}]},{"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha, China"}]},{"given":"Qiujun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha, China"}]},{"given":"Linrui","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha, China"}]},{"given":"Xiang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha, China"}]},{"given":"Xian","family":"Li","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha, China"}]},{"given":"Mengyao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0485-4965","authenticated-orcid":false,"given":"Qing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9845-4251","authenticated-orcid":false,"given":"Yongjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8985-3541","authenticated-orcid":false,"given":"Yansheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0016-2902","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Earth and Space Sciences, Peking University, Beijing, China"}]},{"given":"Yong","family":"Tang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Company Ltd., Shenzhen, China"}]},{"given":"Dapeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Company Ltd., Shenzhen, China"}]},{"given":"Shizhong","family":"Yang","sequence":"additional","affiliation":[{"name":"BDS Micro Chip Inc., Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1173-6593","authenticated-orcid":false,"given":"Haifeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02613"},{"key":"ref3","article-title":"PointLLM: Empowering large language models to understand point clouds","author":"Xu","year":"2023","journal-title":"arXiv:2308.16911"},{"key":"ref4","first-page":"2437","article-title":"TableVLM: Multi-modal pre-training for table structure recognition","volume-title":"Proc. 61st Annu. Meeting Assoc. Comput. Linguistics Long Papers","author":"Chen"},{"key":"ref5","article-title":"OneLLM: One framework to align all modalities with language","author":"Han","year":"2023","journal-title":"arXiv:2312.03700"},{"key":"ref6","article-title":"Meta-transformer: A unified framework for multimodal learning","author":"Zhang","year":"2023","journal-title":"arXiv:2307.10802"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2023.128913"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111637"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3248871"},{"key":"ref10","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Qi"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.12.077"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.01.003"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref16","first-page":"1","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref17","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref18","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref19","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3271312"},{"key":"ref21","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.09.009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"ref24","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","volume":"1","author":"Kenton"},{"key":"ref25","volume-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref26","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref27","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref28","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2018.04.050"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2815613"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2551720"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00240"},{"key":"ref36","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00985"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00144"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.09.012"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.07.007"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/rs10050800"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2969024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3233847"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3097093"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.05.011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3336285"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3294495"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref49","article-title":"What matters in training a GPT4-style language model with multimodal inputs","author":"Zeng","year":"2023","journal-title":"arXiv:2307.02469"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414142"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00887"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615160"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3136287"},{"key":"ref55","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref56","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref57","first-page":"142","article-title":"Learning word vectors for sentiment analysis","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Maas"},{"key":"ref58","article-title":"CodeSearchNet challenge: Evaluating the state of semantic code search","author":"Husain","year":"2019","journal-title":"arXiv:1909.09436"},{"key":"ref59","first-page":"1","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3033336"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3099033"},{"key":"ref64","article-title":"Few-shot learning with graph neural networks","author":"Garcia","year":"2017","journal-title":"arXiv:1711.04043"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2017.0457"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459260"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2007.01089.x"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1117\/12.242059"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2010.2055033"},{"key":"ref74","first-page":"298","article-title":"Structural high-resolution satellite image indexing","volume-title":"Proc. 7th ISPRS TC Symp.","author":"Xia"},{"key":"ref75","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015","journal-title":"arXiv:1512.03012"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01731-4"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3390\/rs11050494"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071369"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2783902"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2920374"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2983560"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3092816"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3109661"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3026221"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3127851"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3093914"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3262840"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS52108.2023.10283090"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190850"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3126082"},{"key":"ref94","article-title":"Vision models are more robust and fair when pretrained on uncurated images without supervision","author":"Goyal","year":"2022","journal-title":"arXiv:2202.08360"},{"key":"ref95","article-title":"Dino-mc: Self-supervised contrastive learning for remote sensing imagery with multi-sized local crops","author":"Wanyan","year":"2023","journal-title":"arXiv:2303.06670"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.3390\/s23052499"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3021527"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07175-8"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.3390\/atmos13101719"},{"key":"ref100","article-title":"GraphCodeBERT: Pre-training code representations with data flow","author":"Guo","year":"2020","journal-title":"arXiv:2009.08366"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.99"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983410"},{"key":"ref103","first-page":"1","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Qi"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00979"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.086"},{"key":"ref106","article-title":"PointGPT: Auto-regressively generative pre-training from point clouds","author":"Chen","year":"2023","journal-title":"arXiv:2305.11487"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2013.120340"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2321565"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2421440"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/7.913670"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2013.120378"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref114","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xie"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016940"},{"key":"ref116","article-title":"Adversarial training methods for semi-supervised text classification","author":"Miyato","year":"2016","journal-title":"arXiv:1605.07725"},{"key":"ref117","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref118","first-page":"5753","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang"},{"key":"ref119","article-title":"ERNIE-doc: A retrospective long-document modeling transformer","author":"Ding","year":"2020","journal-title":"arXiv:2012.15688"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3428360"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.08.015"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10830573.pdf?arnumber=10830573","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:44:04Z","timestamp":1767206644000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10830573\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":122,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3526725","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}