{"id":"https://openalex.org/W4388740367","doi":"https://doi.org/10.1109/tgrs.2023.3333375","title":"Exploring Uni-Modal Feature Learning on Entities and Relations for Remote Sensing Cross-Modal Text-Image Retrieval","display_name":"Exploring Uni-Modal Feature Learning on Entities and Relations for Remote Sensing Cross-Modal Text-Image Retrieval","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4388740367","doi":"https://doi.org/10.1109/tgrs.2023.3333375"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2023.3333375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2023.3333375","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/A5101557084","display_name":"Shun Zhang","orcid":"https://orcid.org/0000-0003-3380-8957"},"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":"Shun Zhang","raw_affiliation_strings":["School of Electronic and Information, Northwestern Polytechnical University, Xi’an, China","School of Electronic and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032102573","display_name":"Yupeng Li","orcid":"https://orcid.org/0000-0003-1429-5009"},"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":"Yupeng Li","raw_affiliation_strings":["School of Electronic and Information, Northwestern Polytechnical University, Xi’an, China","School of Electronic and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067207818","display_name":"Shaohui Mei","orcid":"https://orcid.org/0000-0002-8018-596X"},"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":"Shaohui Mei","raw_affiliation_strings":["School of Electronic and Information, Northwestern Polytechnical University, Xi’an, China","School of Electronic and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, P.R. China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101557084"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":4.5737,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.96116226,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"61","issue":null,"first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9904999732971191,"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":0.8222542405128479},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6289063096046448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.55451899766922},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5446597337722778},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.507916271686554},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48037558794021606},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.46180716156959534},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45002394914627075},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.43729260563850403},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4132433533668518},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3821741044521332},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3730372488498688},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.3408660590648651},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2470685839653015}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222542405128479},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6289063096046448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.55451899766922},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5446597337722778},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.507916271686554},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48037558794021606},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.46180716156959534},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45002394914627075},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.43729260563850403},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4132433533668518},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3821741044521332},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3730372488498688},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3408660590648651},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2470685839653015},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2023.3333375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2023.3333375","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":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5521239382","display_name":null,"funder_award_id":"62171381","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6393876729","display_name":null,"funder_award_id":"62271409","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1536680647","https://openalex.org/W1924770834","https://openalex.org/W1977556410","https://openalex.org/W2067983738","https://openalex.org/W2095483845","https://openalex.org/W2101105183","https://openalex.org/W2158703410","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2401246392","https://openalex.org/W2510520237","https://openalex.org/W2603566245","https://openalex.org/W2618530766","https://openalex.org/W2740924709","https://openalex.org/W2774267535","https://openalex.org/W2779054585","https://openalex.org/W2896457183","https://openalex.org/W2946417913","https://openalex.org/W2962964995","https://openalex.org/W2963910742","https://openalex.org/W2964120214","https://openalex.org/W2964331819","https://openalex.org/W2971086219","https://openalex.org/W2981448908","https://openalex.org/W2986670728","https://openalex.org/W2994818707","https://openalex.org/W2996180937","https://openalex.org/W3004137323","https://openalex.org/W3088680480","https://openalex.org/W3093905312","https://openalex.org/W3098711604","https://openalex.org/W3100245404","https://openalex.org/W3117344638","https://openalex.org/W3133744039","https://openalex.org/W3140792177","https://openalex.org/W3154766321","https://openalex.org/W3165084071","https://openalex.org/W3170863103","https://openalex.org/W3191251640","https://openalex.org/W3208803664","https://openalex.org/W3217792975","https://openalex.org/W4206111836","https://openalex.org/W4206706211","https://openalex.org/W4211112734","https://openalex.org/W4224269597","https://openalex.org/W4224911357","https://openalex.org/W4226359564","https://openalex.org/W4283216168","https://openalex.org/W4296079338","https://openalex.org/W4312611884","https://openalex.org/W4312685069","https://openalex.org/W4312808420","https://openalex.org/W4313121711","https://openalex.org/W4313156423","https://openalex.org/W4313260363","https://openalex.org/W4313476697","https://openalex.org/W4362652984","https://openalex.org/W4378696930","https://openalex.org/W4381790494","https://openalex.org/W4385245566","https://openalex.org/W4400728888","https://openalex.org/W6629028937","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6747225742","https://openalex.org/W6755207826","https://openalex.org/W6766978945","https://openalex.org/W6771887216","https://openalex.org/W6778883912","https://openalex.org/W6796761347","https://openalex.org/W6854290347"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2184288218","https://openalex.org/W2947282851","https://openalex.org/W2374066281","https://openalex.org/W4387423606","https://openalex.org/W2071180033","https://openalex.org/W2036058638","https://openalex.org/W2528082075","https://openalex.org/W155590726"],"abstract_inverted_index":{"Remote":[0],"sensing":[1,24],"cross-modal":[2,35,91],"text-image":[3],"retrieval":[4,58],"(RSCTIR)":[5],"has":[6],"recently":[7],"received":[8],"unprecedented":[9],"attention":[10,157],"due":[11],"to":[12,54,79,130,162,229],"its":[13,105],"advantages":[14],"of":[15,50,57,99,107,136,144,150,172,186,234,257],"flexible":[16],"input":[17],"and":[18,40,43,87,115,120,152,167,180,183,200,221,249],"efficient":[19],"query":[20],"on":[21,33,71,85,202,243,261],"enormous":[22],"remote":[23],"(RS)":[25],"images.":[26],"However,":[27],"most":[28],"RSCTIR":[29,68,175,245,263],"methods":[30,191],"focus":[31],"obsessively":[32],"the":[34,48,55,62,90,100,112,132,164,170,174,195,203,231,254,258,262],"semantic":[36,153,196],"alignment":[37],"between":[38,198],"text":[39,227],"image":[41,216,219],"modalities":[42],"are":[44],"easily":[45],"stuck":[46],"in":[47,89,236],"dilemma":[49],"information":[51,185],"redundancy,":[52],"leading":[53],"degradation":[56],"accuracy.":[59],"To":[60],"address":[61],"issues,":[63],"we":[64,96,206],"construct":[65],"a":[66,208,226],"novel":[67,209],"framework":[69],"based":[70],"mask-guided":[72,156],"relation":[73],"modeling":[74],"with":[75,125,169],"entity":[76,211,220],"loss":[77,204],"(MGRM-EL),":[78],"fully":[80],"explore":[81],"uni-modal":[82,118,177,210],"feature":[83,148],"learning":[84,93,178],"entities":[86,235],"relations":[88,135,143],"model":[92],"process.":[94],"Specifically,":[95],"take":[97],"advantage":[98],"Transformer":[101,122],"encoder":[102],"architecture":[103],"for":[104,146],"ability":[106,179],"capturing":[108],"long-distance":[109],"dependencies":[110],"from":[111],"global":[113],"view,":[114],"build":[116],"two":[117],"(visual":[119],"textual)":[121],"encoders":[123],"combined":[124],"convolutional":[126],"neural":[127],"network":[128],"(CNN)":[129],"extract":[131],"spatial":[133],"inter-region":[134],"images":[137,199],"as":[138,140,217],"well":[139],"long-term":[141],"inter-word":[142],"texts":[145,201,224],"prominent":[147],"embedding":[149],"visual":[151],"representations.":[154],"A":[155],"strategy":[158],"is":[159],"further":[160],"introduced":[161],"learn":[163,230],"salient":[165],"regions":[166],"words,":[168],"aim":[171],"enhancing":[173],"model\u2019s":[176],"eliminating":[181],"unnecessary":[182],"redundant":[184],"each":[187,215,237],"modality.":[188,238],"Unlike":[189],"existing":[190],"that":[192],"simply":[193],"compute":[194],"similarity":[197],"functions,":[205],"present":[207],"loss,":[212],"which":[213,252],"treats":[214],"an":[218],"merges":[222],"similar":[223],"into":[225],"entity,":[228],"independent":[232],"distribution":[233],"We":[239],"conduct":[240],"extensive":[241],"experiments":[242],"public":[244],"benchmarks":[246],"including":[247],"RSICD":[248],"RSITMD":[250],"datasets,":[251],"demonstrate":[253],"state-of-the-art":[255],"performance":[256],"proposed":[259],"method":[260],"task.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":13}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}