{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T05:04:58Z","timestamp":1774674298211,"version":"3.50.1"},"reference-count":51,"publisher":"Informa UK Limited","issue":"1","license":[{"start":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T00:00:00Z","timestamp":1681948800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Digital Earth"],"published-print":{"date-parts":[[2023,10,2]]},"DOI":"10.1080\/17538947.2023.2202423","type":"journal-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T11:57:04Z","timestamp":1681991824000},"page":"1469-1490","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":30,"title":["MDvT: introducing mobile three-dimensional convolution to a vision transformer for hyperspectral image classification"],"prefix":"10.1080","volume":"16","author":[{"given":"Xinyao","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Geographical Sciences, Southwest University, Chongqing, People\u2019s Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzuo","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Geographical Sciences, Southwest University, Chongqing, People\u2019s Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoli","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Geographical Sciences, Southwest University, Chongqing, People\u2019s Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichen","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Geographical Sciences, Southwest University, Chongqing, People\u2019s Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2023,4,20]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11273-009-9169-z"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs13030516"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2584107"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2012.2216272"},{"key":"e_1_3_3_6_1","unstructured":"Devlin Jacob Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2018. \u201cBert: Pre-training of Deep Bidirectional Transformers for Language Understanding.\u201d arXiv preprint arXiv:1810.04805."},{"key":"e_1_3_3_7_1","unstructured":"Dosovitskiy Alexey Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani et al. 2020. \u201cAn Image is Worth 16(16 Words: Transformers for Image Recognition at Scale.\u201d arXiv preprint arXiv:2010.11929."},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2197589"},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.08.011"},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs13030498"},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3172371"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2021.3064051"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"e_1_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2978268"},{"key":"e_1_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2021.147758"},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46805-6_19"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2725580"},{"key":"e_1_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3007811"},{"key":"e_1_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1080\/10095020.2021.2017237"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1707.02921"},{"key":"e_1_3_3_21_1","first-page":"10012","article-title":"Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows","author":"Liu Ze","year":"2021","unstructured":"Liu, Ze, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. \u201cSwin Transformer: Hierarchical Vision Transformer Using Shifted Windows.\u201d International Conference on Computer Vision (ICCV), 10012\u201310022. arXiv preprint arXiv:2103.14030.","journal-title":"International Conference on Computer Vision (ICCV)"},{"key":"e_1_3_3_22_1","unstructured":"Loshchilov Ilya and Frank Hutter. 2017. \u201cDecoupled Weight Decay Regularization.\u201d arXiv preprint arXiv:1711.05101."},{"key":"e_1_3_3_23_1","first-page":"256","article-title":"Tree Species Classification from Airborne Hyperspectral and LiDAR Data Using 3D Convolutional Neural Networks","author":"Mayra J.","year":"2021","unstructured":"Mayra, J., S. Keski-Saari, S. Kivinen, T. Tanhuanpaa, P. Hurskainen, P. Kullberg, L. Poikolainen, et al. 2021. \u201cTree Species Classification from Airborne Hyperspectral and LiDAR Data Using 3D Convolutional Neural Networks.\u201d Remote Sensing of Environment, 256. d oi:ART N 112322 1 0.10 16\/j.rse.2021.112322.","journal-title":"Remote Sensing of Environment"},{"key":"e_1_3_3_24_1","unstructured":"Mehta Sachin and Mohammad Rastegari. 2021. \u201cMobilevit: Light-Weight General-Purpose and Mobile-Friendly Vision Transformer.\u201d arXiv preprint arXiv:2110.02178."},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2004.831865"},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2636241"},{"key":"e_1_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2017.11.021"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.09.006"},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.03889"},{"key":"e_1_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3043267"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.06.006"},{"key":"e_1_3_3_32_1","first-page":"4510","article-title":"Mobilenetv2: Inverted Residuals and Linear Bottlenecks","author":"Sandler Mark","year":"2018","unstructured":"Sandler, Mark, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. 2018. \u201cMobilenetv2: Inverted Residuals and Linear Bottlenecks.\u201d Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4510\u20134520. arXiv:1801.04381.","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs12152495"},{"key":"e_1_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1080\/15440478.2023.2172638"},{"key":"e_1_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2011.08.002"},{"key":"e_1_3_3_36_1","first-page":"5998","article-title":"Attention is all you Need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. \u201cAttention is all you Need.\u201d Advances in Neural Information Processing Systems 30: 5998\u20136008. arXiv:1706.03762.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_37_1","doi-asserted-by":"crossref","unstructured":"Wang Xiaolong Ross Girshick Abhinav Gupta and Kaiming He. 2018. Non-Local Neural Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2477537"},{"key":"e_1_3_3_39_1","doi-asserted-by":"crossref","unstructured":"Wang Alex Amanpreet Singh Julian Michael Felix Hill Omer Levy and Samuel R Bowman. 2018. \u201cGLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding.\u201d arXiv preprint arXiv:1804.07461.","DOI":"10.18653\/v1\/W18-5446"},{"key":"e_1_3_3_40_1","first-page":"568","article-title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction Without Convolutions","author":"Wang Wenhai","year":"2021","unstructured":"Wang, Wenhai, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. 2021. \u201cPyramid Vision Transformer: A Versatile Backbone for Dense Prediction Without Convolutions.\u201d International Conference on Computer Vision (ICCV), 568\u2013578. arXiv:2102.12122.","journal-title":"International Conference on Computer Vision (ICCV)"},{"key":"e_1_3_3_41_1","unstructured":"Wu Zhanghao Zhijian Liu Ji Lin Yujun Lin and Song Han. 2020. \u201cLite Transformer with Long-Short Range Attention.\u201d arXiv preprint arXiv:2004.11886."},{"key":"e_1_3_3_42_1","first-page":"22","article-title":"CvT: Introducing Convolutions to Vision Transformers","author":"Wu H.","year":"2021","unstructured":"Wu, H., B. Xiao, N. Codella, M. Liu, X. Dai, L. Yuan, and L. Zhang. 2021. \u201cCvT: Introducing Convolutions to Vision Transformers.\u201d Proceedings of the IEEE\/CVF International Conference on Computer Vision, 22\u201331.","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"e_1_3_3_43_1","doi-asserted-by":"crossref","unstructured":"Yang Baosong Longyue Wang Derek Wong Lidia S Chao and Zhaopeng Tu. 2019. \u201cConvolutional Self-Attention Networks.\u201d arXiv preprint arXiv:1904.03107.","DOI":"10.18653\/v1\/N19-1407"},{"key":"e_1_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.09.010"},{"key":"e_1_3_3_45_1","first-page":"558","article-title":"Tokens-to-token vit: Training Vision Transformers from Scratch on Imagenet","author":"Yuan Li","year":"2021","unstructured":"Yuan, Li, Yunpeng Chen, Tao Wang, Weihao Yu, Yujun Shi, Zi-Hang Jiang, Francis EH Tay, Jiashi Feng, and Shuicheng Yan. 2021. \u201cTokens-to-token vit: Training Vision Transformers from Scratch on Imagenet.\u201d Proceedings of the IEEE\/CVF International Conference on Computer Vision, 558\u2013567. arXiv:2101.11986.","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"e_1_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2484324"},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/2150704X.2015.1047045"},{"key":"e_1_3_3_48_1","unstructured":"Zaremba Wojciech Ilya Sutskever and Oriol Vinyals. 2014. \u201cRecurrent Neural Network Regularization.\u201d arXiv preprint arXiv:1409.2329."},{"key":"e_1_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2020.111938"},{"key":"e_1_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"e_1_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2020.112012"},{"key":"e_1_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2018.2867592"}],"container-title":["International Journal of Digital Earth"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/17538947.2023.2202423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T09:57:45Z","timestamp":1700474265000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/17538947.2023.2202423"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,20]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,10,2]]}},"alternative-id":["10.1080\/17538947.2023.2202423"],"URL":"https:\/\/doi.org\/10.1080\/17538947.2023.2202423","relation":{},"ISSN":["1753-8947","1753-8955"],"issn-type":[{"value":"1753-8947","type":"print"},{"value":"1753-8955","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,20]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tjde20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tjde20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2022-12-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-08","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}