{"id":"https://openalex.org/W4404809303","doi":"https://doi.org/10.1109/tgrs.2024.3502800","title":"Hierarchical Multimodality Graph Reasoning for Remote Sensing Visual Question Answering","display_name":"Hierarchical Multimodality Graph Reasoning for Remote Sensing Visual Question Answering","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404809303","doi":"https://doi.org/10.1109/tgrs.2024.3502800"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3502800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3502800","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/A5100399261","display_name":"Han Zhang","orcid":"https://orcid.org/0000-0001-7750-0028"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Han Zhang","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0001-7750-0028","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705665","display_name":"Ke\u2010Ming Wang","orcid":"https://orcid.org/0000-0002-7181-754X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keming Wang","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089417036","display_name":"Laixian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148107","display_name":"Space Engineering University","ror":"https://ror.org/04rj1td02","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210148107"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Laixian Zhang","raw_affiliation_strings":["Key Laboratory of Intelligent Space TTC&#x0026;O, Space Engineering University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Space TTC&#x0026;O, Space Engineering University, Beijing, China","institution_ids":["https://openalex.org/I4210148107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042066946","display_name":"Bingshu Wang","orcid":"https://orcid.org/0000-0002-2603-8328"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingshu Wang","raw_affiliation_strings":["School of Software, Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-2603-8328","affiliations":[{"raw_affiliation_string":"School of Software, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106943753","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2924-946X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["China Telecom Corporation, Institute of Artificial Intelligence (TeleAI), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2924-946X","affiliations":[{"raw_affiliation_string":"China Telecom Corporation, Institute of Artificial Intelligence (TeleAI), Beijing, China","institution_ids":["https://openalex.org/I4210136246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100399261"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":10.746,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98314634,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9769999980926514,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.9758999943733215,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7335174679756165},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5770666599273682},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5636566281318665},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.42613595724105835},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41450393199920654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4066067636013031},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.3619856536388397},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.236454576253891},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.105828195810318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7335174679756165},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5770666599273682},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5636566281318665},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42613595724105835},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41450393199920654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4066067636013031},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3619856536388397},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.236454576253891},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.105828195810318}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2024.3502800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3502800","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/G449060228","display_name":null,"funder_award_id":"TC2023JC23","funder_id":"https://openalex.org/F4320336567","funder_display_name":"Natural Science Basic Research Program of Shaanxi Province"},{"id":"https://openalex.org/G8669932268","display_name":null,"funder_award_id":"62406249","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/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2546696630","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2597425697","https://openalex.org/W2732016772","https://openalex.org/W2747623286","https://openalex.org/W2896457183","https://openalex.org/W2896902935","https://openalex.org/W2916723116","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963383024","https://openalex.org/W2963466731","https://openalex.org/W2963518342","https://openalex.org/W2963644680","https://openalex.org/W2963717374","https://openalex.org/W2964023275","https://openalex.org/W2964138017","https://openalex.org/W2966683369","https://openalex.org/W2998014937","https://openalex.org/W3004349648","https://openalex.org/W3012111773","https://openalex.org/W3037773948","https://openalex.org/W3098351727","https://openalex.org/W3136761610","https://openalex.org/W3152635550","https://openalex.org/W3168972675","https://openalex.org/W3176330035","https://openalex.org/W3186187670","https://openalex.org/W3194015448","https://openalex.org/W3216623900","https://openalex.org/W4229439310","https://openalex.org/W4285818301","https://openalex.org/W4292828962","https://openalex.org/W4294658750","https://openalex.org/W4307321662","https://openalex.org/W4316661266","https://openalex.org/W4386453561","https://openalex.org/W4386472879","https://openalex.org/W4387546267","https://openalex.org/W4387885730","https://openalex.org/W4390873421","https://openalex.org/W6715144786","https://openalex.org/W6728881024","https://openalex.org/W6752404935","https://openalex.org/W6791353385","https://openalex.org/W6802006682"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W2385859805","https://openalex.org/W4212839359"],"abstract_inverted_index":{"Remote":[0],"sensing":[1],"visual":[2,28,43],"question":[3],"answering":[4,7],"(RSVQA)":[5],"targets":[6],"the":[8,39,49,67,104,129,131,138,149,174,200],"questions":[9],"about":[10],"RS":[11],"images":[12],"in":[13,18,36,62],"natural":[14],"language":[15,125],"form.":[16],"RSVQA":[17,37],"real-world":[19],"applications":[20],"is":[21,144,197],"always":[22],"challenging,":[23],"which":[24,94,116,146],"may":[25],"contain":[26],"wide-field":[27],"information":[29,46,177],"and":[30,44,47,65,101,123,137,153,160,191,208],"complicated":[31],"queries.":[32],"The":[33],"current":[34],"methods":[35],"overlook":[38],"semantic":[40,133,155,180],"hierarchy":[41],"of":[42,52,157,176,206],"linguistic":[45],"ignore":[48],"complex":[50,150],"relations":[51,156],"multimodal":[53,106,140],"instances.":[54,162],"Thus,":[55],"they":[56],"severely":[57],"suffer":[58],"from":[59],"vital":[60],"deficiencies":[61],"comprehensively":[63],"representing":[64],"associating":[66],"vision\u2013language":[68,98,113,132],"semantics.":[69],"In":[70],"this":[71],"research,":[72],"we":[73,109,164],"design":[74,110],"an":[75],"innovative":[76],"end-to-end":[77],"model,":[78],"named":[79],"<underline":[80,83,86,89],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[81,84,87,90],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">H</u>ierarchical":[82],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</u>ultimodality":[85],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">G</u>raph":[88],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</u>easoning":[91],"(HMGR)":[92],"network,":[93],"hierarchically":[95],"learns":[96],"multigranular":[97],"joint":[99],"representations,":[100,130],"interactively":[102],"parses":[103],"heterogeneous":[105],"relationships.":[107],"Specifically,":[108],"a":[111,166,204],"hierarchical":[112],"encoder":[114],"(HVLE),":[115],"could":[117,147],"simultaneously":[118],"represent":[119],"multiscale":[120],"vision":[121,207],"features":[122],"multilevel":[124],"features.":[126],"Based":[127],"on":[128,184],"graphs":[134],"are":[135],"built,":[136],"parallel":[139],"graph":[141],"relation":[142],"reasoning":[143],"posed,":[145],"explore":[148],"interaction":[151],"patterns":[152],"implicit":[154],"both":[158],"intramodality":[159],"intermodality":[161],"Moreover,":[163],"raise":[165],"distinctive":[167],"vision\u2013question":[168],"(VQ)":[169],"feature":[170],"fusion":[171],"module":[172],"for":[173],"collaboration":[175],"at":[178],"different":[179],"levels.":[181],"Extensive":[182],"experiments":[183],"three":[185],"public":[186],"large-scale":[187],"datasets":[188],"(RSVQA-LR,":[189],"RSVQA-HRv1,":[190],"RSVQA-HRv2)":[192],"demonstrate":[193],"that":[194],"our":[195],"work":[196],"superior":[198],"to":[199],"state-of-the-art":[201],"results":[202],"toward":[203],"mass":[205],"query":[209],"types.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}