{"id":"https://openalex.org/W4312915946","doi":"https://doi.org/10.1109/igarss46834.2022.9883199","title":"Capformer: Pure Transformer for Remote Sensing Image Caption","display_name":"Capformer: Pure Transformer for Remote Sensing Image Caption","publication_year":2022,"publication_date":"2022-07-17","ids":{"openalex":"https://openalex.org/W4312915946","doi":"https://doi.org/10.1109/igarss46834.2022.9883199"},"language":"en","primary_location":{"id":"doi:10.1109/igarss46834.2022.9883199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss46834.2022.9883199","pdf_url":null,"source":{"id":"https://openalex.org/S4363604196","display_name":"IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062779308","display_name":"Junjue Wang","orcid":"https://orcid.org/0000-0002-9500-3399"},"institutions":[{"id":"https://openalex.org/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjue Wang","raw_affiliation_strings":["State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing","institution_ids":["https://openalex.org/I4210118728"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046711799","display_name":"Zihang Chen","orcid":"https://orcid.org/0000-0002-7437-7850"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihang Chen","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University,Wuhan,China,430079"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University,Wuhan,China,430079","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030713988","display_name":"Ailong Ma","orcid":"https://orcid.org/0000-0003-3692-6473"},"institutions":[{"id":"https://openalex.org/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ailong Ma","raw_affiliation_strings":["State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing","institution_ids":["https://openalex.org/I4210118728"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100754351","display_name":"Yanfei Zhong","orcid":"https://orcid.org/0000-0001-9446-5850"},"institutions":[{"id":"https://openalex.org/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfei Zhong","raw_affiliation_strings":["State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing","institution_ids":["https://openalex.org/I4210118728"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5337,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.88791084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7996","last_page":"7999"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9986000061035156,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7937643527984619},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7303473353385925},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6483187079429626},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.580891489982605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5779625177383423},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5266342759132385},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4636446535587311},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.4442433714866638},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09943971037864685},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09727156162261963},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09016036987304688},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07938632369041443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7937643527984619},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7303473353385925},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6483187079429626},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.580891489982605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5779625177383423},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5266342759132385},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4636446535587311},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.4442433714866638},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09943971037864685},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09727156162261963},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09016036987304688},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07938632369041443},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igarss46834.2022.9883199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss46834.2022.9883199","pdf_url":null,"source":{"id":"https://openalex.org/S4363604196","display_name":"IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G7094697349","display_name":null,"funder_award_id":"42071350,42171336","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W2151103935","https://openalex.org/W2745461083","https://openalex.org/W2779054585","https://openalex.org/W2829067510","https://openalex.org/W2896348597","https://openalex.org/W2969711198","https://openalex.org/W3100245404","https://openalex.org/W3103318792","https://openalex.org/W3124149278","https://openalex.org/W3165726526","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6789705400"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W4317547544","https://openalex.org/W4313395829"],"abstract_inverted_index":{"Accurately":[0],"describing":[1],"high-spatial":[2],"resolution":[3],"remote":[4,55],"sensing":[5,56],"images":[6],"requires":[7],"the":[8,10,14,17,29,39,70,88,99,105,121,124],"understanding":[9],"inner":[11],"attributes":[12],"of":[13,31,41],"objects":[15],"and":[16,102,113],"outer":[18],"relations":[19],"between":[20],"different":[21],"objects.":[22],"The":[23,94,111],"existing":[24],"image":[25,57,67,89,106,126],"caption":[26,127],"algorithms":[27],"lack":[28],"ability":[30],"global":[32,71],"representation,":[33,68],"which":[34],"are":[35],"not":[36],"fit":[37],"for":[38,54,66],"summarization":[40],"complex":[42],"scenes.":[43],"To":[44],"this":[45],"end,":[46],"we":[47],"propose":[48],"a":[49,60],"pure":[50],"transformer":[51,63,81,95],"(CapFormer)":[52],"architecture":[53],"caption.":[58],"Specifically,":[59],"scalable":[61],"vision":[62],"is":[64,83],"adopted":[65],"where":[69],"content":[72],"can":[73],"be":[74],"captured":[75],"with":[76,104],"multi-head":[77],"self-attention":[78],"layers.":[79,110],"A":[80],"decoder":[82,96],"designed":[84],"to":[85],"successively":[86],"translate":[87],"features":[90,107],"into":[91],"comprehensive":[92,112],"sentences.":[93],"explicitly":[97],"model":[98],"historical":[100],"words":[101],"interact":[103],"using":[108],"cross-attention":[109],"ablation":[114],"experiments":[115],"on":[116],"RSICD":[117],"dataset":[118],"demonstrate":[119],"that":[120],"CapFormer":[122],"outperforms":[123],"state-of-the-art":[125],"methods.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}