{"id":"https://openalex.org/W4394863100","doi":"https://doi.org/10.1109/lgrs.2024.3389042","title":"Enhancing Remote Sensing Visual Question Answering: A Mask-Based Dual-Stream Feature Mutual Attention Network","display_name":"Enhancing Remote Sensing Visual Question Answering: A Mask-Based Dual-Stream Feature Mutual Attention Network","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394863100","doi":"https://doi.org/10.1109/lgrs.2024.3389042"},"language":"en","primary_location":{"id":"doi:10.1109/lgrs.2024.3389042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lgrs.2024.3389042","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/A5100356496","display_name":"Yangyang Li","orcid":"https://orcid.org/0000-0002-1328-8889"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyang Li","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-1328-8889","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101758969","display_name":"Yunfei Ma","orcid":"https://orcid.org/0009-0004-6276-1435"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfei Ma","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0004-6276-1435","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050045954","display_name":"Guangyuan Liu","orcid":"https://orcid.org/0000-0003-2725-0918"},"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/I4210115570","display_name":"National Space Science Center","ror":"https://ror.org/02nnjtm50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210115570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyuan Liu","raw_affiliation_strings":["National Space Science Center, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2725-0918","affiliations":[{"raw_affiliation_string":"National Space Science Center, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210115570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101737182","display_name":"Qiang Wei","orcid":"https://orcid.org/0000-0002-9109-5943"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wei","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049747868","display_name":"Yanqiao Chen","orcid":"https://orcid.org/0000-0001-6228-852X"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanqiao Chen","raw_affiliation_strings":["54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054791684","display_name":"Ronghua Shang","orcid":"https://orcid.org/0000-0001-9124-696X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghua Shang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-9124-696X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050630882","display_name":"Licheng Jiao","orcid":"https://orcid.org/0000-0003-3354-9617"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Licheng Jiao","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-3354-9617","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9738,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86903729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"21","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7435510158538818},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.660868227481842},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6330407857894897},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5875225067138672},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4747077524662018},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39505645632743835},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3408845067024231},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.3204822838306427},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10029718279838562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7435510158538818},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.660868227481842},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6330407857894897},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5875225067138672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4747077524662018},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39505645632743835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3408845067024231},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3204822838306427},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10029718279838562},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lgrs.2024.3389042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lgrs.2024.3389042","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/G2678691044","display_name":null,"funder_award_id":"62101517","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2700949206","display_name":null,"funder_award_id":"62176200","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2255466643","https://openalex.org/W2593886839","https://openalex.org/W2604086375","https://openalex.org/W2792827505","https://openalex.org/W2896457183","https://openalex.org/W2966683369","https://openalex.org/W3012111773","https://openalex.org/W3098351727","https://openalex.org/W3102127038","https://openalex.org/W3127131334","https://openalex.org/W3128055887","https://openalex.org/W3184761517","https://openalex.org/W4229439310","https://openalex.org/W4285818301","https://openalex.org/W4312845279","https://openalex.org/W4316661266","https://openalex.org/W4385151993","https://openalex.org/W4385245566","https://openalex.org/W4387188337","https://openalex.org/W6755207826","https://openalex.org/W6780226713"],"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/W4212839359","https://openalex.org/W2115758952"],"abstract_inverted_index":{"The":[0,31],"visual":[1,71],"question":[2,52,72,114],"answering":[3,73],"(VQA)":[4],"method":[5,128],"applied":[6],"to":[7,48,97,112,129,156],"remote":[8,69],"sensing":[9,70],"images":[10],"(RSIs)":[11],"can":[12],"complete":[13],"the":[14,40,46,51,56,78,87,93,102,117,125,132,139,162,164,167,201,212,225],"interaction":[15],"of":[16,45,58,92,131,166],"image":[17,47,94,99],"information":[18,44,53],"and":[19,42,54,101,104,122,178],"text":[20],"information,":[21],"which":[22],"avoids":[23],"professional":[24],"barriers":[25],"in":[26,36,138,196],"different":[27],"RSIs":[28],"processing":[29],"fields.":[30],"current":[32],"methods":[33],"face":[34],"challenges":[35],"both":[37],"fully":[38],"utilizing":[39],"global":[41],"local":[43],"interact":[49],"with":[50,124],"addressing":[55],"issue":[57],"inter-class":[59],"interference.":[60],"To":[61],"address":[62],"these":[63],"challenges,":[64],"this":[65],"paper":[66],"proposes":[67],"a":[68,150,186,193],"(RSVQA)":[74],"model":[75,187],"based":[76,148],"on":[77,149,224],"mask-based":[79],"dual-stream":[80,88,133],"feature":[81,89,107],"mutual":[82],"attention":[83,118],"network":[84],"(MADNet).":[85],"First,":[86],"extraction":[90],"module":[91,109,147],"is":[95,110,120,154,170,205,215],"used":[96,111],"obtain":[98,113],"features,":[100],"deep":[103],"shallow":[105],"layer":[106],"encoding":[108],"features.":[115],"Second,":[116],"mechanism":[119],"introduced":[121],"combined":[123],"pointwise":[126],"multiplication":[127],"utilize":[130],"features":[134],"that":[135,188],"were":[136],"extracted":[137],"earlier":[140],"step.":[141],"Finally,":[142],"an":[143],"answer":[144],"relevance":[145],"modulation":[146],"binary":[151],"mask":[152],"vector":[153],"implemented":[155],"filter":[157],"out":[158],"irrelevant":[159],"answers.":[160],"In":[161,181],"experiments,":[163],"performance":[165],"proposed":[168],"strategy":[169],"evaluated":[171],"using":[172],"two":[173],"datasets":[174],"collected":[175],"by":[176,217,221],"aerial":[177],"Sentinel-2":[179],"sensors.":[180],"our":[182,222],"study,":[183],"we":[184],"propose":[185],"outperforms":[189],"previous":[190],"approaches,":[191],"achieving":[192],"6.89%":[194],"increase":[195],"overall":[197],"accuracy":[198],"(OA)":[199],"over":[200],"baseline.":[202],"This":[203],"enhancement":[204],"notable":[206],"for":[207],"its":[208],"persistence,":[209],"even":[210],"when":[211],"training":[213],"data":[214],"reduced":[216],"half,":[218],"as":[219],"evidenced":[220],"experiments":[223],"low-resolution":[226],"dataset.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}