{"id":"https://openalex.org/W4402461727","doi":"https://doi.org/10.1080/17538947.2024.2400988","title":"Region-guided transformer for remote sensing image captioning","display_name":"Region-guided transformer for remote sensing image captioning","publication_year":2024,"publication_date":"2024-09-11","ids":{"openalex":"https://openalex.org/W4402461727","doi":"https://doi.org/10.1080/17538947.2024.2400988"},"language":"en","primary_location":{"id":"doi:10.1080/17538947.2024.2400988","is_oa":true,"landing_page_url":"https://doi.org/10.1080/17538947.2024.2400988","pdf_url":null,"source":{"id":"https://openalex.org/S199162493","display_name":"International Journal of Digital Earth","issn_l":"1753-8947","issn":["1753-8947","1753-8955"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Digital Earth","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1080/17538947.2024.2400988","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101934583","display_name":"Kai Zhao","orcid":"https://orcid.org/0000-0002-2441-6532"},"institutions":[{"id":"https://openalex.org/I4210148107","display_name":"Space Engineering University","ror":"https://ror.org/04rj1td02","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210148107"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Zhao","raw_affiliation_strings":["National Key Laboratory of Space Target Awareness, Space Engineering University, Beijing, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Space Target Awareness, Space Engineering University, Beijing, People's Republic of China","institution_ids":["https://openalex.org/I4210148107"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101760811","display_name":"Wei Xiong","orcid":"https://orcid.org/0000-0002-1399-5559"},"institutions":[{"id":"https://openalex.org/I4210148107","display_name":"Space Engineering University","ror":"https://ror.org/04rj1td02","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210148107"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xiong","raw_affiliation_strings":["Science and Technology on Complex Electronic System Simulation Laboratory, Space Engineering University, Beijing, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Complex Electronic System Simulation Laboratory, Space Engineering University, Beijing, People's Republic of China","institution_ids":["https://openalex.org/I4210148107"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101934583"],"corresponding_institution_ids":["https://openalex.org/I4210148107"],"apc_list":{"value":2390,"currency":"USD","value_usd":2390},"apc_paid":{"value":2390,"currency":"USD","value_usd":2390},"fwci":0.2317,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51176435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"17","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7253886461257935},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.5565348863601685},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4967647194862366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49655061960220337},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.45159173011779785},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41468381881713867},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38922908902168274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34848856925964355},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.3355281352996826},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20655065774917603},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11513277888298035}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7253886461257935},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.5565348863601685},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4967647194862366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49655061960220337},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.45159173011779785},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41468381881713867},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38922908902168274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34848856925964355},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.3355281352996826},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20655065774917603},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11513277888298035},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/17538947.2024.2400988","is_oa":true,"landing_page_url":"https://doi.org/10.1080/17538947.2024.2400988","pdf_url":null,"source":{"id":"https://openalex.org/S199162493","display_name":"International Journal of Digital Earth","issn_l":"1753-8947","issn":["1753-8947","1753-8955"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Digital Earth","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a8e25ddac9f84cfb8cefaeed3a542395","is_oa":true,"landing_page_url":"https://doaj.org/article/a8e25ddac9f84cfb8cefaeed3a542395","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Digital Earth, Vol 17, Iss 1 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1080/17538947.2024.2400988","is_oa":true,"landing_page_url":"https://doi.org/10.1080/17538947.2024.2400988","pdf_url":null,"source":{"id":"https://openalex.org/S199162493","display_name":"International Journal of Digital Earth","issn_l":"1753-8947","issn":["1753-8947","1753-8955"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Digital Earth","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W639708223","https://openalex.org/W1687846465","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2071027807","https://openalex.org/W2101105183","https://openalex.org/W2109586012","https://openalex.org/W2130942839","https://openalex.org/W2131846894","https://openalex.org/W2159243025","https://openalex.org/W2194775991","https://openalex.org/W2221837760","https://openalex.org/W2510520237","https://openalex.org/W2560645892","https://openalex.org/W2564898401","https://openalex.org/W2603566245","https://openalex.org/W2745461083","https://openalex.org/W2779054585","https://openalex.org/W2963175879","https://openalex.org/W2979924880","https://openalex.org/W2986670728","https://openalex.org/W3042724941","https://openalex.org/W3100245404","https://openalex.org/W3131188204","https://openalex.org/W3194015448","https://openalex.org/W4200169950","https://openalex.org/W4200394859","https://openalex.org/W4206028074","https://openalex.org/W4206111836","https://openalex.org/W4213449032","https://openalex.org/W4214587440","https://openalex.org/W4292968451","https://openalex.org/W4310459386","https://openalex.org/W4312389717","https://openalex.org/W4313021481","https://openalex.org/W4361009677","https://openalex.org/W4383748367","https://openalex.org/W4385864244","https://openalex.org/W4389091674"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757"],"abstract_inverted_index":{"Remote":[0],"sensing":[1,15,29,40],"image":[2,23,30,149],"acquisition":[3],"is":[4,87],"an":[5],"essential":[6],"way":[7],"to":[8,74,101,109,116,138,174],"obtain":[9],"information.":[10,141],"However,":[11],"research":[12],"on":[13,19,60,118],"remote":[14,28,39],"images":[16],"mainly":[17],"focuses":[18],"object":[20],"detection":[21],"or":[22],"classification.":[24],"The":[25,179],"emergence":[26],"of":[27,38,66,113,126,161,183],"captioning":[31],"(RSIC)":[32],"has":[33],"enabled":[34],"understanding":[35],"and":[36,63,148,181],"inference":[37],"images,":[41],"thus":[42],"attracting":[43],"considerable":[44],"attention.":[45],"There":[46],"are":[47,57],"still":[48],"challenges":[49],"in":[50,55,99],"RSIC:":[51],"the":[52,72,76,102,111,114,119,124,144,158,176],"features":[53,67,108,137,163],"used":[54],"RSIC":[56],"mostly":[58],"based":[59],"grid":[61],"features,":[62,150],"this":[64],"form":[65],"makes":[68],"it":[69],"difficult":[70],"for":[71,89],"model":[73,115,185],"determine":[75],"main":[77,120],"description":[78],"targets.":[79,121],"Hence,":[80],"a":[81,96,153,165],"more":[82],"effective":[83],"cross-modal":[84],"matching":[85,145],"method":[86],"needed":[88],"better":[90],"text":[91,147],"generation.":[92],"Thus,":[93],"we":[94,134,151,170],"propose":[95,152],"region-guided":[97,154,172],"transformer":[98],"response":[100],"aforementioned":[103],"issues.":[104],"We":[105],"extracted":[106],"region":[107,131],"enhance":[110],"ability":[112],"focus":[117],"To":[122,142],"address":[123],"issue":[125],"information":[127,173],"loss":[128],"caused":[129],"by":[130],"feature":[132],"extraction,":[133],"proposed":[135],"environment":[136],"supplement":[139],"background":[140],"improve":[143],"between":[146],"decoder":[155],"that":[156],"enhances":[157],"model's":[159],"perception":[160],"different":[162],"through":[164,189],"weighted":[166],"cross-attention":[167],"mechanism.":[168],"Meanwhile,":[169],"introduce":[171],"guide":[175],"text-generation":[177],"process.":[178],"effectiveness":[180],"superiority":[182],"our":[184],"have":[186],"been":[187],"demonstrated":[188],"extensive":[190],"experiments.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}