{"id":"https://openalex.org/W4408145414","doi":"https://doi.org/10.1109/tgrs.2025.3547988","title":"RS-MoE: A Vision\u2013Language Model With Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering","display_name":"RS-MoE: A Vision\u2013Language Model With Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408145414","doi":"https://doi.org/10.1109/tgrs.2025.3547988"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2025.3547988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3547988","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/A5101799777","display_name":"Hui Lin","orcid":"https://orcid.org/0000-0003-0190-969X"},"institutions":[{"id":"https://openalex.org/I4210130112","display_name":"China Academy of Information and Communications Technology","ror":"https://ror.org/038dte259","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210130112","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Lin","raw_affiliation_strings":["China Academy of Electronics and Information Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0190-969X","affiliations":[{"raw_affiliation_string":"China Academy of Electronics and Information Technology, Beijing, China","institution_ids":["https://openalex.org/I4210130112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075013625","display_name":"Danfeng Hong","orcid":"https://orcid.org/0000-0002-3212-9584"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danfeng Hong","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3212-9584","affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084278666","display_name":"Shaodi Ge","orcid":"https://orcid.org/0000-0003-3638-1602"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Shuhang Ge","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates","Department of Electrical and Computer Engineering, New York University Abu Dhabi, Abu Dhabi, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University Abu Dhabi, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075046622","display_name":"Chuyao Luo","orcid":"https://orcid.org/0000-0003-4848-609X"},"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":"Chuyao Luo","raw_affiliation_strings":["Department of Computer Science, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4848-609X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Jiang","orcid":"https://orcid.org/0000-0003-2784-8397"},"institutions":[{"id":"https://openalex.org/I4210130112","display_name":"China Academy of Information and Communications Technology","ror":"https://ror.org/038dte259","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210130112","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Jiang","raw_affiliation_strings":["China Academy of Electronics and Information Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2784-8397","affiliations":[{"raw_affiliation_string":"China Academy of Electronics and Information Technology, Beijing, China","institution_ids":["https://openalex.org/I4210130112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603359","display_name":"Hao Jin","orcid":"https://orcid.org/0009-0001-1932-9178"},"institutions":[{"id":"https://openalex.org/I4210130112","display_name":"China Academy of Information and Communications Technology","ror":"https://ror.org/038dte259","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210130112","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Jin","raw_affiliation_strings":["China Academy of Electronics and Information Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-1932-9178","affiliations":[{"raw_affiliation_string":"China Academy of Electronics and Information Technology, Beijing, China","institution_ids":["https://openalex.org/I4210130112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062799681","display_name":"Congcong Wen","orcid":"https://orcid.org/0000-0001-6448-003X"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Congcong Wen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates","Department of Electrical and Computer Engineering, New York University Abu Dhabi, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0001-6448-003X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University Abu Dhabi, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I120250893"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.0761,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.99313947,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9965000152587891,"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":0.9207000136375427,"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":0.8979605436325073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7328609824180603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.554548442363739},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.5192615985870361},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5141825675964355},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48741939663887024},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4427468478679657},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32244205474853516},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0885019600391388}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8979605436325073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7328609824180603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.554548442363739},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.5192615985870361},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5141825675964355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48741939663887024},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4427468478679657},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32244205474853516},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0885019600391388}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3547988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3547988","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":[],"awards":[{"id":"https://openalex.org/G3927219227","display_name":null,"funder_award_id":"L222041","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G5277594389","display_name":null,"funder_award_id":"2024124","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G7398995703","display_name":null,"funder_award_id":"U24B20177","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"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W92662927","https://openalex.org/W2150884987","https://openalex.org/W2221837760","https://openalex.org/W2510520237","https://openalex.org/W2603566245","https://openalex.org/W2779054585","https://openalex.org/W2790047899","https://openalex.org/W2809290718","https://openalex.org/W2911584214","https://openalex.org/W2995904231","https://openalex.org/W3006487741","https://openalex.org/W3017628311","https://openalex.org/W3038038411","https://openalex.org/W3154766321","https://openalex.org/W3168972675","https://openalex.org/W3172942063","https://openalex.org/W3196922338","https://openalex.org/W3198377975","https://openalex.org/W3216736520","https://openalex.org/W4211112734","https://openalex.org/W4214587440","https://openalex.org/W4220716465","https://openalex.org/W4229439310","https://openalex.org/W4312389717","https://openalex.org/W4316661266","https://openalex.org/W4323824384","https://openalex.org/W4381049901","https://openalex.org/W4387402974","https://openalex.org/W4391766847","https://openalex.org/W4392900447","https://openalex.org/W4393906060","https://openalex.org/W4394966885","https://openalex.org/W4395041667","https://openalex.org/W4399572612","https://openalex.org/W4400828729","https://openalex.org/W4402263153","https://openalex.org/W4402727764","https://openalex.org/W4404927137","https://openalex.org/W4406258412","https://openalex.org/W6791353385","https://openalex.org/W6796487566","https://openalex.org/W6810855181","https://openalex.org/W6838461096","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6853116092","https://openalex.org/W6854878091","https://openalex.org/W6856800273","https://openalex.org/W6857872576","https://openalex.org/W6858816293","https://openalex.org/W6860277257","https://openalex.org/W6860795172","https://openalex.org/W6861475616","https://openalex.org/W6861774121","https://openalex.org/W6862592012","https://openalex.org/W6862974260","https://openalex.org/W6870183580","https://openalex.org/W6871553294","https://openalex.org/W6871629594","https://openalex.org/W6873338258","https://openalex.org/W6875465148","https://openalex.org/W6875466976"],"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],"sensing":[1,53,89,106,300],"image":[2],"captioning":[3],"(RSIC)":[4],"presents":[5],"unique":[6,85],"challenges":[7],"and":[8,21,32,55,126,182,264],"plays":[9],"a":[10,122,172,206],"critical":[11],"role":[12],"in":[13,39,261],"applications":[14],"such":[15],"as":[16,133],"environmental":[17],"monitoring,":[18],"urban":[19],"planning,":[20],"disaster":[22],"management.":[23],"Traditional":[24],"RSIC":[25,70,159],"methods":[26],"often":[27],"struggle":[28],"to":[29,46,56,63,76,83,141,152,169,215,220,275],"produce":[30],"rich":[31],"diverse":[33],"descriptions.":[34],"Recently,":[35],"with":[36,242],"significant":[37],"advancements":[38],"vision-language":[40],"models":[41,49,71,81,131],"(VLMs),":[42],"efforts":[43],"have":[44],"emerged":[45],"integrate":[47],"these":[48,77],"into":[50],"the":[51,84,95,112,117,158,176,180,185,191,194,227,238,279,298],"remote":[52,88,105,299],"domain":[54],"introduce":[57],"richly":[58],"descriptive":[59],"datasets":[60,78,247],"specifically":[61,102],"designed":[62,140],"enhance":[64],"VLM":[65,101],"training.":[66],"However,":[67],"most":[68],"current":[69],"generally":[72],"apply":[73],"only":[74,164],"fine-tuning":[75,251],"without":[79],"developing":[80],"tailored":[82,145],"characteristics":[86],"of":[87,98,114,157,175,184,193,200,281],"imagery.":[90],"This":[91,161],"article":[92],"proposes":[93],"RS-MoE,":[94],"first":[96],"mixture":[97],"expert":[99,134,167],"(MoE)-based":[100],"customized":[103],"for":[104,146,210],"domain.":[107],"Unlike":[108],"traditional":[109,246],"MoE":[110,118],"models,":[111],"core":[113],"RS-MoE":[115,213],"is":[116,139],"block,":[119],"which":[120],"incorporates":[121],"novel":[123],"instruction":[124,137],"router":[125,138],"multiple":[127],"lightweight":[128],"large":[129],"language":[130],"(LLMs)":[132],"models.":[135],"The":[136],"generate":[142],"specific":[143,173],"prompts":[144],"each":[147,166],"corresponding":[148],"LLM,":[149],"guiding":[150],"them":[151],"focus":[153],"on":[154,171,226,237,244,297],"distinct":[155],"aspects":[156],"task.":[160,305],"design":[162],"not":[163],"allows":[165],"LLM":[168],"concentrate":[170],"subset":[174],"task,":[177],"thereby":[178],"enhancing":[179],"specificity":[181],"accuracy":[183],"generated":[186],"captions,":[187],"but":[188],"also":[189],"improves":[190],"scalability":[192],"model":[195,214,225,257,283,287],"by":[196,292],"facilitating":[197],"parallel":[198],"processing":[199],"subtasks.":[201],"In":[202],"addition,":[203],"we":[204],"present":[205],"two-stage":[207],"training":[208,233],"strategy":[209],"tuning":[211],"our":[212,224,231,256,269,282,286],"prevent":[216],"performance":[217,260,273,296],"degradation":[218],"due":[219],"sparsity.":[221],"We":[222],"fine-tuned":[223],"RSICap":[228,239],"dataset":[229],"using":[230],"proposed":[232],"strategy.":[234],"Experimental":[235],"results":[236],"dataset,":[240],"along":[241],"evaluations":[243],"other":[245],"where":[248],"no":[249],"additional":[250],"was":[252],"applied,":[253],"demonstrate":[254],"that":[255],"achieves":[258,272],"state-of-the-art":[259,295],"generating":[262],"precise":[263],"contextually":[265],"relevant":[266],"captions.":[267],"Notably,":[268],"RS-MoE-1B":[270],"variant":[271],"comparable":[274],"13B":[276],"VLMs,":[277],"demonstrating":[278],"efficiency":[280],"design.":[284],"Moreover,":[285],"demonstrates":[288],"promising":[289],"generalization":[290],"capabilities":[291],"consistently":[293],"achieving":[294],"visual":[301],"question":[302],"answering":[303],"(RSVQA)":[304]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":13}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}