{"id":"https://openalex.org/W4292968451","doi":"https://doi.org/10.1109/tgrs.2022.3201474","title":"NWPU-Captions Dataset and MLCA-Net for Remote Sensing Image Captioning","display_name":"NWPU-Captions Dataset and MLCA-Net for Remote Sensing Image Captioning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4292968451","doi":"https://doi.org/10.1109/tgrs.2022.3201474"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2022.3201474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2022.3201474","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-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/A5101639319","display_name":"Qimin Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qimin Cheng","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057771622","display_name":"Haiyan Huang","orcid":"https://orcid.org/0000-0002-9931-9884"},"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"]},{"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":"Haiyan Huang","raw_affiliation_strings":["State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I4210118728","https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102200212","display_name":"Yuan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Xu","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001602025","display_name":"Yuzhuo Zhou","orcid":"https://orcid.org/0009-0009-7912-6370"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhuo Zhou","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101825551","display_name":"LI Huan-ying","orcid":"https://orcid.org/0009-0002-8370-1015"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanying Li","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741750","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0002-9796-488X"},"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":"Zhongyuan Wang","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, China","School of computer science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of computer science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101639319"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":10.5959,"has_fulltext":false,"cited_by_count":110,"citation_normalized_percentile":{"value":0.98988084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"60","issue":null,"first_page":"1","last_page":"19"},"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":0.9954000115394592,"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":0.9902999997138977,"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/closed-captioning","display_name":"Closed captioning","score":0.7925395369529724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7585617899894714},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.5511221885681152},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5432544350624084},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5181176066398621},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4484533965587616},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.44683343172073364},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43370530009269714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3797909617424011},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27776849269866943},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09838336706161499},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06743177771568298}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7925395369529724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585617899894714},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.5511221885681152},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5432544350624084},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5181176066398621},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4484533965587616},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.44683343172073364},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43370530009269714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3797909617424011},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27776849269866943},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09838336706161499},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06743177771568298},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2022.3201474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2022.3201474","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G693433701","display_name":null,"funder_award_id":"42171434","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G967177310","display_name":null,"funder_award_id":"42090012","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":66,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W956551720","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1980038761","https://openalex.org/W2086866337","https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2220981600","https://openalex.org/W2506483933","https://openalex.org/W2510520237","https://openalex.org/W2546523301","https://openalex.org/W2550553598","https://openalex.org/W2551751523","https://openalex.org/W2575842049","https://openalex.org/W2592962403","https://openalex.org/W2603566245","https://openalex.org/W2604178507","https://openalex.org/W2607151106","https://openalex.org/W2745461083","https://openalex.org/W2754689878","https://openalex.org/W2754927243","https://openalex.org/W2760340275","https://openalex.org/W2779054585","https://openalex.org/W2795151422","https://openalex.org/W2798959609","https://openalex.org/W2808206191","https://openalex.org/W2909102496","https://openalex.org/W2911584214","https://openalex.org/W2920981979","https://openalex.org/W2943885184","https://openalex.org/W2963084599","https://openalex.org/W2963088515","https://openalex.org/W2963138277","https://openalex.org/W2963267809","https://openalex.org/W2963686907","https://openalex.org/W2973586224","https://openalex.org/W2979924880","https://openalex.org/W2986534680","https://openalex.org/W2997056851","https://openalex.org/W3006487741","https://openalex.org/W3011916860","https://openalex.org/W3015625772","https://openalex.org/W3033783894","https://openalex.org/W3034858767","https://openalex.org/W3038038411","https://openalex.org/W3046260628","https://openalex.org/W3046675509","https://openalex.org/W3097754216","https://openalex.org/W3100245404","https://openalex.org/W3102850314","https://openalex.org/W3117344638","https://openalex.org/W3140792177","https://openalex.org/W3154766321","https://openalex.org/W3194015448","https://openalex.org/W3196922338","https://openalex.org/W3198422076","https://openalex.org/W3213119051","https://openalex.org/W6637306801","https://openalex.org/W6638742206","https://openalex.org/W6678262379","https://openalex.org/W6679436768","https://openalex.org/W6685230081","https://openalex.org/W6740021858"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Recently,":[0],"the":[1,12,32,104,149,159,164,175,184],"burgeoning":[2],"demands":[3],"for":[4],"captioning-related":[5],"applications":[6],"have":[7],"inspired":[8],"great":[9],"endeavors":[10],"in":[11,22,89,96,153],"remote":[13,36,154],"sensing":[14,37,155],"community.":[15],"However,":[16],"current":[17,81],"benchmark":[18,58,84],"datasets":[19,85,198],"are":[20,191],"deficient":[21],"data":[23],"volume,":[24],"category":[25],"variety,":[26],"and":[27,55,103,106,117,139,141,161,171,180,187,199],"description":[28],"richness,":[29],"which":[30],"hinders":[31],"advancement":[33],"of":[34,78,100,108,135,163,177,189],"new":[35],"image":[38,133],"captioning":[39],"approaches,":[40],"especially":[41],"those":[42],"based":[43],"on":[44,196],"deep":[45],"learning.":[46],"To":[47],"overcome":[48],"this":[49],"limitation,":[50],"we":[51],"present":[52],"a":[53,112,126,143],"larger":[54,92],"more":[56],"challenging":[57],"dataset,":[59],"termed":[60],"NWPU-Captions.":[61,200],"NWPU-Captions":[62,79],"contains":[63],"157,500":[64],"sentences,":[65],"with":[66],"all":[67],"31,500":[68],"images":[69],"annotated":[70],"manually":[71],"by":[72,173],"7":[73],"experienced":[74],"volunteers.":[75],"The":[76],"superiority":[77],"over":[80],"publicly":[82],"available":[83],"not":[86],"only":[87],"lies":[88],"its":[90,97],"much":[91],"scale":[93,178],"but":[94],"also":[95],"wider":[98],"coverage":[99],"complex":[101],"scenes":[102],"richness":[105],"variety":[107],"describing":[109],"vocabularies.":[110],"Further,":[111],"novel":[113],"encoder-decoder":[114],"architecture,":[115],"multi-level":[116,127],"contextual":[118,144],"attention":[119,128,145],"network":[120],"(MLCA-Net),":[121],"is":[122],"proposed.":[123],"MLCA-Net":[124,157,190],"employs":[125],"module":[129,146],"to":[130,147],"adaptively":[131],"aggregate":[132],"features":[134],"specific":[136],"spatial":[137],"regions":[138],"scales":[140],"introduces":[142],"explore":[148],"latent":[150],"context":[151],"hidden":[152],"images.":[156],"improves":[158],"flexibility":[160],"diversity":[162],"generated":[165],"captions":[166],"while":[167],"keeping":[168],"their":[169],"accuracy":[170],"conciseness":[172],"exploring":[174],"properties":[176],"variations":[179],"semantic":[181],"ambiguity.":[182],"Finally,":[183],"effectiveness,":[185],"robustness,":[186],"generalization":[188],"proved":[192],"through":[193],"extensive":[194],"experiments":[195],"existing":[197]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":53},{"year":2024,"cited_by_count":39},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}