{"id":"https://openalex.org/W4403977279","doi":"https://doi.org/10.1109/tgrs.2024.3489224","title":"Cross-Modal Prealigned Method With Global and Local Information for Remote Sensing Image and Text Retrieval","display_name":"Cross-Modal Prealigned Method With Global and Local Information for Remote Sensing Image and Text Retrieval","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403977279","doi":"https://doi.org/10.1109/tgrs.2024.3489224"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3489224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3489224","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.14704","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zengbao Sun","orcid":"https://orcid.org/0009-0005-3417-8063"},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengbao Sun","raw_affiliation_strings":["Department of Information Engineering, Shanghai Maritime University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-3417-8063","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Shanghai Maritime University, Shanghai, China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101521257","display_name":"Ming Zhao","orcid":"https://orcid.org/0000-0002-1310-6766"},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhao","raw_affiliation_strings":["Department of Information Engineering, Shanghai Maritime University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Shanghai Maritime University, Shanghai, China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009435390","display_name":"Gaorui Liu","orcid":"https://orcid.org/0000-0002-1420-7331"},"institutions":[{"id":"https://openalex.org/I4210135723","display_name":"Shanghai Institute of Technical Physics","ror":"https://ror.org/02txedb84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210135723"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaorui Liu","raw_affiliation_strings":["Key Laboratory of Intelligent Infrared Perception, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Infrared Perception, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210135723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062850220","display_name":"Andr\u00e9 Kaup","orcid":"https://orcid.org/0000-0002-0929-5074"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Kaup","raw_affiliation_strings":["Chair of Multimedia Communications and Signal Processing, Friedrich-Alexander University Erlangen-N&#x00FC;rnberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0929-5074","affiliations":[{"raw_affiliation_string":"Chair of Multimedia Communications and Signal Processing, Friedrich-Alexander University Erlangen-N&#x00FC;rnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4525,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90493966,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"18"},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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":0.9954000115394592,"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/remote-sensing","display_name":"Remote sensing","score":0.7124494910240173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6665440201759338},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5567952394485474},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5114783048629761},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4529725909233093},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42366528511047363},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3780697286128998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34909379482269287},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.17047789692878723}],"concepts":[{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.7124494910240173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665440201759338},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5567952394485474},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5114783048629761},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4529725909233093},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42366528511047363},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3780697286128998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34909379482269287},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.17047789692878723},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tgrs.2024.3489224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3489224","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"},{"id":"pmh:oai:arXiv.org:2411.14704","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.14704","pdf_url":"https://arxiv.org/pdf/2411.14704","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.14704","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.14704","pdf_url":"https://arxiv.org/pdf/2411.14704","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2040950132","display_name":"\u57fa\u4e8e\u591a\u65f6\u7a7a\u5c3a\u5ea6\u534f\u540c\u7684\u7ea2\u5916\u822a\u7a7a\u9065\u611f\u5f71\u50cf\u753b\u5e45\u91cd\u5efa\u65b9\u6cd5","funder_award_id":"20ZR1423500","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"},{"id":"https://openalex.org/G3644875000","display_name":null,"funder_award_id":"20ZR1423500","funder_id":"https://openalex.org/F4320334977","funder_display_name":"Beijing Municipal Natural Science Foundation"},{"id":"https://openalex.org/G3920184056","display_name":null,"funder_award_id":"62101316","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5338284468","display_name":null,"funder_award_id":"62271302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5558092770","display_name":null,"funder_award_id":"20ZR1423500","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334977","display_name":"Beijing Municipal Natural Science Foundation","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403977279.pdf"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W2095483845","https://openalex.org/W2293634267","https://openalex.org/W2401246392","https://openalex.org/W2510520237","https://openalex.org/W2779054585","https://openalex.org/W2798280084","https://openalex.org/W2883311563","https://openalex.org/W2943325261","https://openalex.org/W2962964995","https://openalex.org/W2964120214","https://openalex.org/W2967957126","https://openalex.org/W2970231061","https://openalex.org/W2981448908","https://openalex.org/W2988823324","https://openalex.org/W3003289138","https://openalex.org/W3004137323","https://openalex.org/W3005971801","https://openalex.org/W3014611590","https://openalex.org/W3035485997","https://openalex.org/W3035524453","https://openalex.org/W3082766779","https://openalex.org/W3100245404","https://openalex.org/W3137642335","https://openalex.org/W3138516171","https://openalex.org/W3140792177","https://openalex.org/W3165084071","https://openalex.org/W3175888430","https://openalex.org/W3208314443","https://openalex.org/W3208803664","https://openalex.org/W3213484707","https://openalex.org/W3217792975","https://openalex.org/W4210894218","https://openalex.org/W4224911357","https://openalex.org/W4292968451","https://openalex.org/W4313055764","https://openalex.org/W4313178921","https://openalex.org/W4323896867","https://openalex.org/W4378696930","https://openalex.org/W4385245566","https://openalex.org/W4386025722","https://openalex.org/W4386212341","https://openalex.org/W4386597072","https://openalex.org/W4386952228","https://openalex.org/W4388624611","https://openalex.org/W4388740367","https://openalex.org/W4389474309","https://openalex.org/W4392061609","https://openalex.org/W6640212811","https://openalex.org/W6747225742","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6775188310","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6839204056"],"related_works":["https://openalex.org/W2121524756","https://openalex.org/W782553550","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W1987967678","https://openalex.org/W2320915480","https://openalex.org/W2633218168","https://openalex.org/W4235897794","https://openalex.org/W2059707233"],"abstract_inverted_index":{"In":[0,129],"recent":[1],"years,":[2],"remote":[3,40,86,126,235],"sensing":[4,41,87,127,236],"cross-modal":[5,76],"text-image":[6,237],"retrieval":[7,65,147,169,192],"(RSCTIR)":[8],"has":[9],"attracted":[10],"considerable":[11],"attention":[12,109],"owing":[13],"to":[14,36,49,120,137,159,184],"its":[15],"convenience":[16],"and":[17,29,43,67,81,116,175,181,220,243,270],"information":[18,31,83,101,162],"mining":[19],"capabilities.":[20],"However,":[21],"two":[22],"significant":[23,272],"challenges":[24],"persist:":[25],"effectively":[26,121],"integrating":[27],"global":[28,80,100],"local":[30,82,107,113],"during":[32,167],"feature":[33,52],"extraction":[34],"due":[35],"substantial":[37],"variations":[38],"in":[39,58,262,275],"imagery,":[42],"the":[44,106,139,164,168,186,197,215,226,246,267],"failure":[45],"of":[46,105,125,142,248],"existing":[47],"methods":[48],"adequately":[50],"consider":[51],"prealignment":[53,135],"before":[54],"modal":[55,60,143],"fusion,":[56,144],"resulting":[57],"complex":[59],"interactions":[61],"that":[62],"adversely":[63],"impact":[64],"accuracy":[66],"efficiency.":[68],"To":[69],"address":[70],"these":[71],"challenges,":[72],"we":[73,90,150,195],"propose":[74,151],"a":[75,92,99,134,152,259,271],"prealigned":[77],"method":[78],"with":[79],"(CMPAGL)":[84],"for":[85,207],"imagery.":[88],"Specifically,":[89],"design":[91],"global-Swin":[93],"(Gswin)":[94],"Transformer":[95],"block,":[96],"which":[97],"introduces":[98],"window":[102,108,114,118],"on":[103,214,232,266],"top":[104],"mechanism,":[110],"synergistically":[111],"combining":[112],"self-attention":[115],"global-local":[117],"cross-attention":[119],"capture":[122],"multiscale":[123],"features":[124],"images.":[128],"addition,":[130],"our":[131,249],"approach":[132],"incorporates":[133],"mechanism":[136],"mitigate":[138],"training":[140],"difficulty":[141],"thereby":[145,189],"enhancing":[146,191],"accuracy.":[148,193],"Moreover,":[149],"similarity":[153,165,187],"matrix":[154,166],"reweighting":[155],"(SMR)":[156],"reranking":[157],"algorithm":[158,172],"deeply":[160],"exploit":[161],"from":[163],"process.":[170],"This":[171],"combines":[173],"forward":[174],"backward":[176],"ranking,":[177],"extreme":[178],"difference":[179],"ratio,":[180],"other":[182],"factors":[183],"reweight":[185],"matrix,":[188],"further":[190],"Finally,":[194],"optimize":[196],"triplet":[198],"loss":[199],"function":[200],"by":[201],"introducing":[202],"an":[203],"intraclass":[204],"distance":[205,217,227],"term":[206],"matched":[208,219,229],"image-text":[209],"pairs,":[210],"not":[211],"only":[212],"focusing":[213],"relative":[216],"between":[218],"unmatched":[221],"pairs":[222],"but":[223],"also":[224],"minimizing":[225],"within":[228],"pairs.":[230],"Experiments":[231],"four":[233],"public":[234],"datasets,":[238],"including":[239],"RSICD,":[240],"RSITMD,":[241],"UCM-Captions,":[242],"Sydney-Captions,":[244],"demonstrate":[245],"effectiveness":[247],"proposed":[250],"method,":[251],"achieving":[252],"improvements":[253],"over":[254],"state-of-the-art":[255],"methods,":[256],"such":[257],"as":[258],"2.28%":[260],"increase":[261],"mean":[263],"Recall":[264],"(mR)":[265],"RSITMD":[268],"dataset":[269],"4.65%":[273],"improvement":[274],"R@1.":[276],"The":[277],"code":[278],"is":[279],"available":[280],"at":[281],"<uri":[282],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[283],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/ZbaoSun/CMPAGL</uri>.":[284]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}