{"id":"https://openalex.org/W4400019805","doi":"https://doi.org/10.1109/jstars.2024.3419035","title":"RSMoDM: Multimodal Momentum Distillation Model for Remote Sensing Visual Question Answering","display_name":"RSMoDM: Multimodal Momentum Distillation Model for Remote Sensing Visual Question Answering","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400019805","doi":"https://doi.org/10.1109/jstars.2024.3419035"},"language":"en","primary_location":{"id":"doi:10.1109/jstars.2024.3419035","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2024.3419035","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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 Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/jstars.2024.3419035","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100339791","display_name":"Pengfei Li","orcid":"https://orcid.org/0009-0009-4234-1579"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Li","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0009-4234-1579","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109282686","display_name":"Gang Liu","orcid":"https://orcid.org/0000-0002-7032-8429"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Liu","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-7032-8429","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101400989","display_name":"Jinlong He","orcid":"https://orcid.org/0009-0009-8891-554X"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong He","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0009-8891-554X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080015931","display_name":"Xiangxu Meng","orcid":"https://orcid.org/0000-0001-9842-4044"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxu Meng","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-9842-4044","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006400852","display_name":"Shenjun Zhong","orcid":"https://orcid.org/0000-0001-6542-649X"},"institutions":[{"id":"https://openalex.org/I4210114492","display_name":"National Imaging Facility","ror":"https://ror.org/01kdbsa35","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210114492"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shenjun Zhong","raw_affiliation_strings":["Monash Biomedical Imaging, Monash University, Clayton, VIC, Australia","National Imaging Facility, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6542-649X","affiliations":[{"raw_affiliation_string":"Monash Biomedical Imaging, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"National Imaging Facility, Australia","institution_ids":["https://openalex.org/I4210114492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100451602","display_name":"Xun Chen","orcid":"https://orcid.org/0000-0002-4922-8116"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Chen","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","Institute of Dataspace, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4922-8116","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of Dataspace, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1250,"currency":"USD","value_usd":1250},"apc_paid":{"value":1250,"currency":"USD","value_usd":1250},"fwci":2.3297,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89644274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"17","issue":null,"first_page":"16799","last_page":"16814"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9932000041007996,"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":0.9801999926567078,"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/interpretability","display_name":"Interpretability","score":0.7759473323822021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.77097088098526},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.700295090675354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5823407173156738},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5729243755340576},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5704474449157715},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5295485258102417},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4540191888809204},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43206292390823364},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4283212125301361},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4147592782974243},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3276847004890442}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7759473323822021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77097088098526},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.700295090675354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5823407173156738},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5729243755340576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5704474449157715},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5295485258102417},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4540191888809204},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43206292390823364},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4283212125301361},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4147592782974243},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3276847004890442},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstars.2024.3419035","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2024.3419035","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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 Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:dda33c258c314686b35451ab6f8bcbc8","is_oa":true,"landing_page_url":"https://doaj.org/article/dda33c258c314686b35451ab6f8bcbc8","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":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 16799-16814 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/jstars.2024.3419035","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstars.2024.3419035","pdf_url":null,"source":{"id":"https://openalex.org/S117727964","display_name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","issn_l":"1939-1404","issn":["1939-1404","2151-1535"],"is_oa":true,"is_in_doaj":true,"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 Journal of Selected Topics in Applied Earth Observations and Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4023856508","display_name":null,"funder_award_id":"LH2021F015","funder_id":"https://openalex.org/F4320323085","funder_display_name":"Natural Science Foundation of Heilongjiang Province"}],"funders":[{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2512351403","https://openalex.org/W2525778437","https://openalex.org/W2538244214","https://openalex.org/W2616247523","https://openalex.org/W2783165089","https://openalex.org/W2896457183","https://openalex.org/W2963150162","https://openalex.org/W2963383024","https://openalex.org/W2963954913","https://openalex.org/W2968124245","https://openalex.org/W2981578638","https://openalex.org/W2986943971","https://openalex.org/W2987861506","https://openalex.org/W2996970889","https://openalex.org/W3012111773","https://openalex.org/W3034368386","https://openalex.org/W3035682985","https://openalex.org/W3091588028","https://openalex.org/W3097947628","https://openalex.org/W3098351727","https://openalex.org/W3102564565","https://openalex.org/W3138154797","https://openalex.org/W3140792177","https://openalex.org/W3152083889","https://openalex.org/W3154766321","https://openalex.org/W3168972675","https://openalex.org/W3194015448","https://openalex.org/W3205944634","https://openalex.org/W3206799531","https://openalex.org/W3208803664","https://openalex.org/W3213833596","https://openalex.org/W4206111836","https://openalex.org/W4224911357","https://openalex.org/W4226359564","https://openalex.org/W4229439310","https://openalex.org/W4285818301","https://openalex.org/W4292828962","https://openalex.org/W4307321662","https://openalex.org/W4316661266","https://openalex.org/W4376226279","https://openalex.org/W4384820298","https://openalex.org/W4385373284","https://openalex.org/W4386352883","https://openalex.org/W4387211307","https://openalex.org/W4387546267","https://openalex.org/W4387802575","https://openalex.org/W4390520660","https://openalex.org/W4390690017","https://openalex.org/W4394966885","https://openalex.org/W4404612934","https://openalex.org/W6637373629","https://openalex.org/W6638523607","https://openalex.org/W6727690538","https://openalex.org/W6728881024","https://openalex.org/W6730179637","https://openalex.org/W6739901393","https://openalex.org/W6742999658","https://openalex.org/W6748082341","https://openalex.org/W6752083267","https://openalex.org/W6757817989","https://openalex.org/W6761503440","https://openalex.org/W6767279747","https://openalex.org/W6769906912","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6849177959","https://openalex.org/W6851950068","https://openalex.org/W6858688131","https://openalex.org/W6860746437"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4389981515","https://openalex.org/W4381058564","https://openalex.org/W3003945460","https://openalex.org/W2964413124","https://openalex.org/W4288267738"],"abstract_inverted_index":{"Remote":[0],"sensing":[1],"(RS)":[2],"visual":[3],"question":[4],"answering":[5],"(VQA)":[6],"is":[7,182],"a":[8,14,67,130],"task":[9],"that":[10,34,88,110,163],"answers":[11,58],"questions":[12],"about":[13],"given":[15],"RS":[16,29,39,74,132,159],"image":[17,21,136],"by":[18,185],"utilizing":[19],"both":[20],"and":[22,91],"textual":[23],"information.":[24],"However,":[25],"existing":[26],"methods":[27],"in":[28,38,120,170],"VQA":[30,40,75,160],"overlook":[31],"the":[32,35,55,60,80,85,100,124,142],"fact":[33],"ground":[36,113],"truths":[37],"benchmark":[41],"datasets,":[42],"which":[43],"are":[44],"algorithmically":[45],"generated":[46],"rather":[47],"than":[48],"manually":[49],"annotated,":[50],"may":[51],"not":[52],"always":[53],"represent":[54],"most":[56],"reasonable":[57,108],"to":[59,116],"questions.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,78,122,140],"propose":[66],"multimodal":[68,143],"Momentum":[69],"Distillation":[70],"Model":[71],"(RSMoDM)":[72],"for":[73,95,105,134,148],"tasks.":[76],"Specifically,":[77],"maintain":[79],"momentum":[81],"distillation":[82],"model":[83,101],"during":[84],"training":[86,174],"stage":[87],"generates":[89],"stable":[90],"reliable":[92],"pseudo":[93],"labels":[94],"additional":[96],"supervision,":[97],"effectively":[98],"preventing":[99],"from":[102,112],"being":[103],"penalized":[104],"producing":[106],"other":[107],"outputs":[109],"differ":[111],"truth.":[114],"Additionally,":[115],"address":[117],"domain":[118],"shift":[119],"RS,":[121],"employ":[123],"Vision":[125],"Transformer":[126],"(ViT)":[127],"trained":[128],"on":[129],"large-scale":[131],"dataset":[133],"enhanced":[135],"feature":[137],"extraction.":[138],"Moreover,":[139],"introduce":[141],"fusion":[144],"module":[145],"with":[146,172],"cross-attention":[147],"improved":[149],"cross-modal":[150],"representation":[151],"learning.":[152],"Our":[153],"extensive":[154],"experiments":[155],"across":[156],"three":[157],"different":[158],"datasets":[161],"demonstrate":[162],"RSMoDM":[164],"achieves":[165],"state-of-the-art":[166],"performance,":[167],"particularly":[168],"excelling":[169],"scenarios":[171],"limited":[173],"data.":[175],"The":[176,189],"strong":[177],"interpretability":[178],"of":[179],"our":[180],"method":[181],"further":[183],"evidenced":[184],"visualized":[186],"attention":[187],"maps.":[188],"source":[190],"code":[191],"will":[192],"be":[193],"made":[194],"available":[195],"at":[196],"<uri":[197],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[198],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/pengfeiliHEU/RSMoDM</uri>":[199],".":[200]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}