{"id":"https://openalex.org/W4399146252","doi":"https://doi.org/10.1109/tgrs.2024.3406897","title":"Masking-Based Cross-Modal Remote Sensing Image\u2013Text Retrieval via Dynamic Contrastive Learning","display_name":"Masking-Based Cross-Modal Remote Sensing Image\u2013Text Retrieval via Dynamic Contrastive Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399146252","doi":"https://doi.org/10.1109/tgrs.2024.3406897"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3406897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3406897","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/A5100513107","display_name":"Zuopeng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuopeng Zhao","raw_affiliation_strings":["School of Computer Science and Technology and Artificial Intelligence, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology and Artificial Intelligence, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111309587","display_name":"Xiaoran Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoran Miao","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-6972-9783","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048225135","display_name":"Chen He","orcid":"https://orcid.org/0000-0003-2023-0244"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen He","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2023-0244","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017658038","display_name":"Jianfeng Hu","orcid":"https://orcid.org/0000-0002-0669-4328"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Hu","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102678789","display_name":"Bingbing Min","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingbing Min","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101228791","display_name":"Yumeng Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumeng Gao","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102000132","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0002-9985-9717"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5098933881","display_name":"Kanyaphakphachsorn Pharksuwan","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kanyaphakphachsorn Pharksuwan","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":4.0707,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.95018807,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987999796867371,"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":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.8446053862571716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5888000130653381},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.49264031648635864},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.47665101289749146},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45961400866508484},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4462590515613556},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4415321350097656},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4316328465938568},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43019598722457886},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.41073134541511536},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36624544858932495},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34736934304237366},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.344411164522171},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2564195394515991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8446053862571716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5888000130653381},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.49264031648635864},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.47665101289749146},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45961400866508484},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4462590515613556},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4415321350097656},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4316328465938568},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43019598722457886},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.41073134541511536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36624544858932495},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34736934304237366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.344411164522171},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2564195394515991},{"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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2024.3406897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3406897","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[{"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"}],"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":78,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1980038761","https://openalex.org/W2091280333","https://openalex.org/W2095483845","https://openalex.org/W2101105183","https://openalex.org/W2401246392","https://openalex.org/W2510520237","https://openalex.org/W2603566245","https://openalex.org/W2763822693","https://openalex.org/W2779054585","https://openalex.org/W2894786240","https://openalex.org/W2896457183","https://openalex.org/W2945385604","https://openalex.org/W2962964995","https://openalex.org/W2964120214","https://openalex.org/W2964187781","https://openalex.org/W2965373594","https://openalex.org/W2969876226","https://openalex.org/W2994818707","https://openalex.org/W3003289138","https://openalex.org/W3004137323","https://openalex.org/W3013436746","https://openalex.org/W3022140654","https://openalex.org/W3034999214","https://openalex.org/W3035524453","https://openalex.org/W3038038411","https://openalex.org/W3046260628","https://openalex.org/W3082766779","https://openalex.org/W3090449556","https://openalex.org/W3094502228","https://openalex.org/W3097754216","https://openalex.org/W3100245404","https://openalex.org/W3128181526","https://openalex.org/W3140792177","https://openalex.org/W3165084071","https://openalex.org/W3208803664","https://openalex.org/W4200272616","https://openalex.org/W4206111836","https://openalex.org/W4224911357","https://openalex.org/W4226359564","https://openalex.org/W4230405732","https://openalex.org/W4308703323","https://openalex.org/W4311002506","https://openalex.org/W4312219282","https://openalex.org/W4312272363","https://openalex.org/W4312784228","https://openalex.org/W4313121711","https://openalex.org/W4313181088","https://openalex.org/W4315778358","https://openalex.org/W4378696930","https://openalex.org/W4382998563","https://openalex.org/W4386212341","https://openalex.org/W4386790226","https://openalex.org/W4386952228","https://openalex.org/W4389665280","https://openalex.org/W4391766847","https://openalex.org/W4394938913","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6747225742","https://openalex.org/W6759579507","https://openalex.org/W6763701032","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6769311223","https://openalex.org/W6778883912","https://openalex.org/W6789753369","https://openalex.org/W6790019176","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6796761347","https://openalex.org/W6798805250","https://openalex.org/W6811013733","https://openalex.org/W6853528422","https://openalex.org/W6861046571"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Cross-modal":[0],"remote":[1],"sensing":[2],"image-text":[3,125,215],"retrieval":[4],"(CMRSITR)":[5],"aims":[6],"to":[7,29,43,180,205],"extract":[8,45],"comprehensive":[9,183],"information":[10],"from":[11,47],"diverse":[12],"modalities.":[13],"The":[14],"primary":[15],"challenge":[16],"in":[17,56,167,222,241],"this":[18],"field":[19],"is":[20,107,165,203],"developing":[21],"effective":[22,63],"mappings":[23],"between":[24,114,173,211],"visual":[25,186],"and":[26,75,96,169,175,187],"textual":[27,188],"modalities":[28],"a":[30,136,147,157,192],"shared":[31],"latent":[32],"space.":[33],"Existing":[34],"approaches":[35],"generally":[36],"focus":[37],"on":[38,70,129,229],"utilizing":[39,100],"pre-trained":[40],"unimodal":[41],"models":[42],"independently":[44],"features":[46,74],"each":[48],"modality.":[49],"However,":[50],"these":[51,88],"techniques":[52,67],"often":[53],"fall":[54],"short":[55],"achieving":[57],"the":[58,71,92,111,121,182,207,212,219,235,242],"critical":[59],"alignment":[60,76],"necessary":[61],"for":[62,84],"cross-modal":[64,158],"matching.":[65],"These":[66],"predominantly":[68],"concentrate":[69],"extraction":[72],"of":[73,123,185,214,238],"at":[77,109],"an":[78],"instance":[79],"level,":[80],"suggesting":[81],"potential":[82],"areas":[83],"enhancement.":[85],"To":[86],"address":[87],"limitations,":[89],"we":[90,134,155,190],"introduce":[91,191],"Masked":[93,137],"Interaction":[94,138],"Inferring":[95,139],"Aligning":[97],"(MIIA)":[98],"framework,":[99],"Dynamic":[101],"Contrastive":[102],"Learning":[103],"(DCL).":[104],"This":[105,201],"framework":[106],"adept":[108],"discerning":[110],"intricate":[112],"relationships":[113],"local":[115],"visual-textual":[116],"tokens,":[117],"thereby":[118],"significantly":[119],"bolstering":[120],"congruence":[122],"global":[124],"pairings":[126],"without":[127],"relying":[128],"additional":[130],"prior":[131],"supervision.":[132],"Initially,":[133],"devise":[135],"(MII)":[140],"module,":[141],"which":[142,164],"fosters":[143],"token-level":[144],"interplays":[145],"through":[146],"novel":[148],"masked":[149],"visual-language":[150],"modeling":[151],"approach.":[152],"Following":[153],"this,":[154],"implement":[156],"dynamic":[159],"contrast":[160,224],"learning":[161],"(DCL)":[162],"mechanism,":[163],"instrumental":[166],"capturing":[168],"aligning":[170],"semantic":[171],"correlations":[172],"images":[174],"texts":[176],"more":[177],"effectively.":[178],"Finally,":[179],"ensure":[181],"matching":[184],"embeddings,":[189],"unique":[193],"technique":[194],"known":[195],"as":[196],"Bidirectional":[197],"Distribution":[198],"Matching":[199],"(BDM).":[200],"method":[202],"designed":[204],"minimize":[206],"Kullback-Leibler":[208],"(KL)":[209],"divergence":[210],"distributions":[213],"similarity,":[216],"computed":[217],"using":[218],"negative":[220],"queues":[221],"momentum":[223],"learning.":[225],"Comprehensive":[226],"experiments":[227],"performed":[228],"well-established":[230],"public":[231],"datasets":[232],"consistently":[233],"validate":[234],"state-of-the-art":[236],"performance":[237],"MIIA":[239],"methods":[240],"CMRSITR":[243],"task.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":17}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}