{"id":"https://openalex.org/W4413392591","doi":"https://doi.org/10.1109/lgrs.2025.3601114","title":"CSA-RSIC: Cross-Modal Semantic Alignment for Remote Sensing Image Captioning","display_name":"CSA-RSIC: Cross-Modal Semantic Alignment for Remote Sensing Image Captioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413392591","doi":"https://doi.org/10.1109/lgrs.2025.3601114"},"language":"en","primary_location":{"id":"doi:10.1109/lgrs.2025.3601114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lgrs.2025.3601114","pdf_url":null,"source":{"id":"https://openalex.org/S126920919","display_name":"IEEE Geoscience and Remote Sensing Letters","issn_l":"1545-598X","issn":["1545-598X","1558-0571"],"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 Geoscience and Remote Sensing Letters","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/A5045904147","display_name":"Kangda Cheng","orcid":"https://orcid.org/0000-0001-5525-6423"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kangda Cheng","raw_affiliation_strings":["School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339168","display_name":"Jinlong Liu","orcid":"https://orcid.org/0000-0002-0284-5029"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Liu","raw_affiliation_strings":["School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062187850","display_name":"Rui Mao","orcid":"https://orcid.org/0000-0002-1082-8755"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rui Mao","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","College of Computing and Data Science, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058198609","display_name":"Zhilu Wu","orcid":"https://orcid.org/0000-0002-3402-9093"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhilu Wu","raw_affiliation_strings":["School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100752356","display_name":"Erik Cambria","orcid":"https://orcid.org/0000-0002-3030-1280"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Erik Cambria","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","College of Computing and Data Science, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045904147"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":3.9313,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94328373,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9947999715805054,"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":0.9513999819755554,"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":0.7921660542488098},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.713517963886261},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5739309787750244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4137713611125946},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4053025543689728},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.3501596450805664},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.11137619614601135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921660542488098},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.713517963886261},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5739309787750244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4137713611125946},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4053025543689728},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3501596450805664},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.11137619614601135},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lgrs.2025.3601114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lgrs.2025.3601114","pdf_url":null,"source":{"id":"https://openalex.org/S126920919","display_name":"IEEE Geoscience and Remote Sensing Letters","issn_l":"1545-598X","issn":["1545-598X","1558-0571"],"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 Geoscience and Remote Sensing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G351021156","display_name":null,"funder_award_id":"62071145","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4755697698","display_name":null,"funder_award_id":"62471157","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/W2510520237","https://openalex.org/W2779054585","https://openalex.org/W3007363984","https://openalex.org/W3046675509","https://openalex.org/W4310459386","https://openalex.org/W4396909863","https://openalex.org/W4396941249","https://openalex.org/W4400228558","https://openalex.org/W4402670552","https://openalex.org/W4403183405","https://openalex.org/W4405521165","https://openalex.org/W4405895878","https://openalex.org/W4406857611","https://openalex.org/W4408404929"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Remote":[0,62],"sensing":[1],"image":[2],"captioning":[3],"(RSIC)":[4],"is":[5,154],"an":[6,76],"important":[7],"task":[8],"in":[9,36,181],"environmental":[10],"monitoring":[11],"and":[12,28,41,48,123,138,151,163,186],"disaster":[13,46],"assessment.":[14],"However,":[15],"existing":[16],"methods":[17],"are":[18],"constrained":[19],"by":[20,119],"redundant":[21],"feature":[22,26,117],"interference,":[23],"insufficient":[24],"multi-scale":[25,121],"integration,":[27],"cross-modal":[29],"semantic":[30,42,140,159,184],"gaps,":[31],"leading":[32],"to":[33,100,156],"limited":[34],"performance":[35],"scenarios":[37],"requiring":[38],"fine-grained":[39,137],"descriptions":[40],"integrity,":[43],"such":[44],"as":[45],"assessment":[47],"emergency":[49],"response.":[50],"In":[51],"this":[52],"letter,":[53],"we":[54,74,105],"propose":[55,106],"a":[56,107,115,143],"Cross-Modal":[57],"Semantic":[58],"Alignment":[59],"Model":[60],"for":[61],"Sensing":[63],"Image":[64],"Captioning":[65],"(CSA-RSIC),":[66],"addressing":[67],"these":[68],"challenges":[69],"with":[70,127],"three":[71,168],"innovations.":[72],"First,":[73],"designed":[75],"Adaptive":[77],"Feature":[78,109],"Selection":[79],"Module":[80,111],"(AFSM)":[81],"that":[82,113,147],"generates":[83],"channel":[84],"weights":[85,92],"through":[86],"dual":[87],"pooling.":[88],"The":[89],"AFSM":[90],"dynamically":[91],"the":[93,133,158,171],"most":[94],"informative":[95],"features":[96],"at":[97],"each":[98],"scale":[99],"improve":[101],"caption":[102],"accuracy.":[103,187],"Second,":[104],"Cross-Scale":[108],"Aggregation":[110],"(CFAM)":[112],"constructs":[114],"hierarchical":[116],"pyramid":[118],"aligning":[120],"resolutions":[122],"performs":[124],"attention-guided":[125],"fusion":[126],"enhanced":[128],"weighting":[129],"via":[130],"AFSM,":[131],"ensuring":[132],"effective":[134],"integration":[135],"of":[136,173],"global":[139],"information.":[141],"Finally,":[142],"novel":[144],"loss":[145,153],"function":[146],"combines":[148],"contrastive":[149],"learning":[150],"consistency":[152],"proposed":[155],"enhance":[157],"alignment":[160],"between":[161],"visual":[162],"textual":[164],"features.":[165],"Experiments":[166],"on":[167],"datasets":[169],"show":[170],"advancement":[172],"CSA-RSIC":[174],"over":[175],"strong":[176],"baselines,":[177],"indicating":[178],"its":[179],"effectiveness":[180],"enhancing":[182],"both":[183],"completeness":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}