{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T02:51:06Z","timestamp":1775011866570,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/jstars.2024.3471625","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:28:29Z","timestamp":1727717309000},"page":"18727-18738","source":"Crossref","is-referenced-by-count":36,"title":["A Lightweight Sparse Focus Transformer for Remote Sensing Image Change Captioning"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8541-7837","authenticated-orcid":false,"given":"Dongwei","family":"Sun","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology and the Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China"}]},{"given":"Yajie","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology and the Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1462-7248","authenticated-orcid":false,"given":"Junmin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Information Science, School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7912-3457","authenticated-orcid":false,"given":"Xiangyong","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology and the Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3195692"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9554419"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3218921"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3328224"},{"key":"ref12","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref15","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref17","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mehta","year":"2022"},{"key":"ref18","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chu","year":"2021"},{"key":"ref19","article-title":"Regionvit: Regional-to-local attention for vision transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref21","article-title":"Axial attention in multidimensional transformers","author":"Ho","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref23","first-page":"14541","article-title":"Fast vision transformers with Hilo attention","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Pan","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref26","article-title":"Shuffle transformer: Rethinking spatial shuffle for vision transformer","author":"Huang","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01175"},{"key":"ref28","article-title":"FasterViT: Fast vision transformers with hierarchical attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hatamizadeh","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS52108.2023.10283451"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3321752"},{"key":"ref32","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2969330"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183434"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3154154"},{"key":"ref37","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni","year":"2002"},{"key":"ref38","first-page":"74","article-title":"A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization ACL","volume":"5","author":"Rouge","year":"2004"},{"key":"ref39","first-page":"65","article-title":"An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. Workshop Intrinsic Extrinsic Eval. Measures MT Summarization","author":"Banerjee","year":"2005"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4609443\/10330207\/10700970.pdf?arnumber=10700970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:38:21Z","timestamp":1732667901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10700970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/jstars.2024.3471625","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}