{"id":"https://openalex.org/W4402627291","doi":"https://doi.org/10.1109/tgrs.2024.3464468","title":"Prior-Experience-Based Vision-Language Model for Remote Sensing Image-Text Retrieval","display_name":"Prior-Experience-Based Vision-Language Model for Remote Sensing Image-Text Retrieval","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402627291","doi":"https://doi.org/10.1109/tgrs.2024.3464468"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3464468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3464468","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/A5059262797","display_name":"Xu Tang","orcid":"https://orcid.org/0000-0003-1375-0778"},"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":"Xu Tang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-1375-0778","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, 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/A5111316088","display_name":"Dabiao Huang","orcid":null},"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":"Dabiao Huang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, 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, 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/A5007754848","display_name":"Jingjing Ma","orcid":"https://orcid.org/0000-0002-4354-3692"},"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":"Jingjing Ma","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, 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, 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/A5049776440","display_name":"Xiangrong Zhang","orcid":"https://orcid.org/0000-0003-0379-2042"},"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":"Xiangrong Zhang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0379-2042","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, 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/A5100453033","display_name":"Fang Liu","orcid":"https://orcid.org/0000-0001-9752-9530"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Liu","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information, Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9752-9530","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information, Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"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, 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, 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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":2.447,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90375919,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"13"},"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":0.98580002784729,"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":0.98580002784729,"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":0.9670000076293945,"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/T10757","display_name":"Geographic Information Systems Studies","score":0.9039000272750854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7380821108818054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5426481366157532},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5394760966300964},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.5263306498527527},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5190901756286621},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4080447852611542},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.11486458778381348}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7380821108818054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5426481366157532},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5394760966300964},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.5263306498527527},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5190901756286621},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4080447852611542},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.11486458778381348}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2024.3464468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3464468","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/G1147961060","display_name":null,"funder_award_id":"62276197","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5324547038","display_name":null,"funder_award_id":"62171332","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6970463474","display_name":null,"funder_award_id":"2024GX-YBXM-125","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"},{"id":"https://openalex.org/G913068305","display_name":null,"funder_award_id":"2023-CXTD-09","funder_id":"https://openalex.org/F4320326174","funder_display_name":"Shaanxi Province Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326174","display_name":"Shaanxi Province Postdoctoral Science Foundation","ror":null},{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1980038761","https://openalex.org/W2064675550","https://openalex.org/W2095483845","https://openalex.org/W2098738957","https://openalex.org/W2105482032","https://openalex.org/W2131774270","https://openalex.org/W2194775991","https://openalex.org/W2303172903","https://openalex.org/W2401246392","https://openalex.org/W2510520237","https://openalex.org/W2745461083","https://openalex.org/W2779054585","https://openalex.org/W2896457183","https://openalex.org/W2964015378","https://openalex.org/W2997786074","https://openalex.org/W3004137323","https://openalex.org/W3035524453","https://openalex.org/W3035552787","https://openalex.org/W3093905312","https://openalex.org/W3100245404","https://openalex.org/W3138516171","https://openalex.org/W3140792177","https://openalex.org/W3165084071","https://openalex.org/W3208803664","https://openalex.org/W3209163491","https://openalex.org/W3209859545","https://openalex.org/W3214677295","https://openalex.org/W4224911357","https://openalex.org/W4283455220","https://openalex.org/W4288391342","https://openalex.org/W4294663621","https://openalex.org/W4294811189","https://openalex.org/W4296636440","https://openalex.org/W4297821406","https://openalex.org/W4312272363","https://openalex.org/W4313121711","https://openalex.org/W4313178921","https://openalex.org/W4313181088","https://openalex.org/W4313889909","https://openalex.org/W4362672456","https://openalex.org/W4378696930","https://openalex.org/W4384787738","https://openalex.org/W4385245566","https://openalex.org/W4385614537","https://openalex.org/W4388624611","https://openalex.org/W6755207826","https://openalex.org/W6762718338","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6811013733","https://openalex.org/W6843154862"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Remote":[0],"sensing":[1],"(RS)":[2],"image-text":[3],"retrieval":[4],"(RSITR)":[5],"aims":[6],"to":[7,27,41,86,114,159,186,204,225,251,267],"retrieve":[8],"relevant":[9],"texts":[10],"(RS":[11],"images)":[12],"based":[13,176],"on":[14,177,288],"the":[15,29,51,61,74,102,109,129,136,151,178,183,188,206,228,243,269,276,281,293,310],"content":[16],"of":[17,76,131,271,312],"a":[18,115,141,168,196,211,218,248,258],"given":[19],"RS":[20,77,90,111,147,163,192,316],"image":[21],"(text).":[22],"Existing":[23],"methods":[24],"are":[25,105,157,286,338],"used":[26,158],"employing":[28],"convolutional":[30],"neural":[31,36],"network":[32,37],"(CNN)":[33],"and":[34,44,97,154,165,217,235,246,292,315,332],"recurrent":[35],"(RNN)":[38],"as":[39,327],"encoders":[40,156],"learn":[42],"visual":[43,94,153,184,234],"textual":[45,103,236],"features":[46,161,245],"for":[47,182,255],"retrieval.":[48,256],"Although":[49],"feasible,":[50],"global":[52],"information":[53],"hidden":[54],"in":[55,81,89,93,119,280,323],"different":[56,120,231],"data":[57,278],"does":[58],"not":[59],"receive":[60],"attention":[62],"it":[63],"deserves.":[64],"To":[65,134],"mitigate":[66],"this":[67],"problem,":[68],"transformers":[69],"have":[70],"been":[71],"introduced.":[72],"Nevertheless,":[73],"complexity":[75],"images":[78,164,193],"present":[79],"challenges":[80],"directly":[82],"introducing":[83],"Transformer-based":[84],"architectures":[85],"multimodal":[87,198,213],"learning":[88,259],"scenes,":[91],"particularly":[92],"feature":[95,170],"extraction":[96],"cross-modal":[98,207,244],"interaction.":[99],"In":[100],"addition,":[101],"captions":[104],"always":[106],"simpler":[107],"than":[108],"complex":[110,189],"images,":[112,317],"leading":[113],"semantic":[116],"description":[117],"appearing":[118],"images.":[121],"This":[122],"typical":[123],"false-negative":[124],"(FN)":[125],"sample":[126],"problem":[127],"increases":[128],"difficulty":[130],"RSITR":[132,143],"tasks.":[133],"address":[135],"above":[137],"limitations,":[138],"we":[139],"propose":[140],"new":[142],"model":[144,282,300],"named":[145],"prior-experience-based":[146],"vision-language":[148],"(PERSVL).":[149],"First,":[150],"specific":[152],"text":[155],"extract":[160],"from":[162,191,260],"texts.":[166],"Also,":[167],"high-level":[169],"complement":[171],"(HFC)":[172],"module":[173,216,241,264],"is":[174,202,223,265],"developed":[175],"self-attention":[179],"mechanism":[180],"(SAM)":[181],"encoder":[185,200],"explore":[187,227],"contents":[190],"fully.":[194],"Second,":[195],"dual-branch":[197,212],"fusion":[199,220,240],"(DBMFE)":[201],"designed":[203,224,266],"complete":[205],"learning.":[208],"It":[209],"comprises":[210],"interaction":[214],"(DBMI)":[215],"branch":[219,239],"module.":[221],"DBMI":[222],"fully":[226],"relationships":[229],"between":[230],"modalities,":[232],"enriching":[233],"features.":[237],"The":[238],"integrates":[242],"utilizes":[247],"classification":[249],"head":[250],"generate":[252],"matching":[253],"scores":[254],"Finally,":[257],"prior":[261],"experiences":[262],"(LPEs)":[263],"reduce":[268],"influence":[270],"FN":[272],"samples":[273],"by":[274],"analyzing":[275],"historical":[277],"produced":[279],"training":[283],"process.":[284],"Experiments":[285],"conducted":[287],"three":[289],"popular":[290],"datasets,":[291],"positive":[294],"results":[295],"show":[296],"that":[297],"our":[298,318],"PERSVL":[299,319],"achieves":[301],"superior":[302],"performance":[303],"compared":[304],"with":[305],"previous":[306],"methods.":[307],"By":[308],"integrating":[309],"advantages":[311],"natural":[313],"language":[314],"can":[320],"be":[321],"applied":[322],"various":[324],"applications,":[325],"such":[326],"environmental":[328],"monitoring,":[329],"disaster":[330],"evaluation,":[331],"urban":[333],"planning.":[334],"Our":[335],"source":[336],"codes":[337],"available":[339],"at:https://github.com/TangXu-Group/Cross-modal-remote-sensing-image-and-text-retrieval-models/tree/main/PERSVL.":[340]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":10}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}