{"id":"https://openalex.org/W4386913007","doi":"https://doi.org/10.3390/rs15184637","title":"A Fusion Encoder with Multi-Task Guidance for Cross-Modal Text\u2013Image Retrieval in Remote Sensing","display_name":"A Fusion Encoder with Multi-Task Guidance for Cross-Modal Text\u2013Image Retrieval in Remote Sensing","publication_year":2023,"publication_date":"2023-09-21","ids":{"openalex":"https://openalex.org/W4386913007","doi":"https://doi.org/10.3390/rs15184637"},"language":"en","primary_location":{"id":"doi:10.3390/rs15184637","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15184637","pdf_url":"https://www.mdpi.com/2072-4292/15/18/4637/pdf?version=1695298294","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2072-4292/15/18/4637/pdf?version=1695298294","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103477851","display_name":"Xiong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiong Zhang","raw_affiliation_strings":["School of Information and Communication, National University of Defense Technology, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430074, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719482","display_name":"Weipeng Li","orcid":"https://orcid.org/0000-0002-9337-0996"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weipeng Li","raw_affiliation_strings":["School of Information and Communication, National University of Defense Technology, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430074, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407870","display_name":"Xu Wang","orcid":"https://orcid.org/0000-0002-3988-9121"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Wang","raw_affiliation_strings":["School of Information and Communication, National University of Defense Technology, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430074, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385092","display_name":"Luyao Wang","orcid":"https://orcid.org/0000-0001-9275-1896"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luyao Wang","raw_affiliation_strings":["School of Information and Communication, National University of Defense Technology, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430074, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101187266","display_name":"Fuzhong Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuzhong Zheng","raw_affiliation_strings":["School of Information and Communication, National University of Defense Technology, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430074, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447536","display_name":"Long Wang","orcid":"https://orcid.org/0000-0001-5600-8157"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Wang","raw_affiliation_strings":["School of Information and Communication, National University of Defense Technology, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430074, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069050052","display_name":"Haisu Zhang","orcid":"https://orcid.org/0000-0001-7823-6257"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haisu Zhang","raw_affiliation_strings":["School of Information and Communication, National University of Defense Technology, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430074, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5069050052"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":2500,"currency":"CHF","value_usd":2707},"apc_paid":{"value":2500,"currency":"CHF","value_usd":2707},"fwci":1.5495,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8538059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"15","issue":"18","first_page":"4637","last_page":"4637"},"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":0.9991999864578247,"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":0.995199978351593,"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":0.8549176454544067},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5653212070465088},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5130173563957214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49930286407470703},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4480654001235962},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4374930262565613},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.384652316570282},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3596496284008026},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33441218733787537},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.278940886259079}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8549176454544067},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5653212070465088},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5130173563957214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49930286407470703},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4480654001235962},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4374930262565613},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.384652316570282},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3596496284008026},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33441218733787537},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.278940886259079},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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":2,"locations":[{"id":"doi:10.3390/rs15184637","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15184637","pdf_url":"https://www.mdpi.com/2072-4292/15/18/4637/pdf?version=1695298294","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b32d599baa5c484994e6fa10d6147734","is_oa":true,"landing_page_url":"https://doaj.org/article/b32d599baa5c484994e6fa10d6147734","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing, Vol 15, Iss 18, p 4637 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/rs15184637","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15184637","pdf_url":"https://www.mdpi.com/2072-4292/15/18/4637/pdf?version=1695298294","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2570225071","display_name":null,"funder_award_id":"62102423","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8740608253","display_name":null,"funder_award_id":"6210242","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386913007.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1689711448","https://openalex.org/W2096733369","https://openalex.org/W2138621090","https://openalex.org/W2156387975","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2510520237","https://openalex.org/W2552579943","https://openalex.org/W2603566245","https://openalex.org/W2619383789","https://openalex.org/W2779054585","https://openalex.org/W2962964995","https://openalex.org/W2970231061","https://openalex.org/W2981448908","https://openalex.org/W3004137323","https://openalex.org/W3035524453","https://openalex.org/W3035682985","https://openalex.org/W3100245404","https://openalex.org/W3108655343","https://openalex.org/W3111501160","https://openalex.org/W3140792177","https://openalex.org/W3165084071","https://openalex.org/W3171007011","https://openalex.org/W3208803664","https://openalex.org/W3217792975","https://openalex.org/W4224911357","https://openalex.org/W4226172762","https://openalex.org/W4283721482","https://openalex.org/W4289654394","https://openalex.org/W4308068144","https://openalex.org/W4311002506","https://openalex.org/W6682889407","https://openalex.org/W6796339025","https://openalex.org/W6802704712","https://openalex.org/W6804635132","https://openalex.org/W6810559079"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2119949815"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"there":[3],"has":[4,117],"been":[5,118],"a":[6,100,214],"growing":[7],"interest":[8],"in":[9,28,88,120,176,191],"remote":[10,32,53,160,185],"sensing":[11,33,37,54,161,186],"image\u2013text":[12,135],"cross-modal":[13,45,122],"retrieval":[14,46,123,209,215,221],"due":[15],"to":[16,155,171,197,235],"the":[17,25,29,44,50,108,113,121,130,143,166,173,199,237,241],"rapid":[18],"development":[19],"of":[20,31,52,67,72,75,115,124],"space":[21],"information":[22],"technology":[23],"and":[24,91,142,163,180,194,207,240],"significant":[26,189],"increase":[27],"volume":[30],"image":[34],"data.":[35],"Remote":[36],"images":[38,55,85,162,187],"have":[39],"unique":[40],"characteristics":[41],"that":[42],"make":[43],"task":[47,168],"challenging.":[48],"Firstly,":[49],"semantics":[51],"are":[56],"fine-grained,":[57],"meaning":[58],"they":[59],"can":[60,78],"be":[61],"divided":[62],"into":[63],"multiple":[64],"basic":[65,73],"units":[66,74],"semantic":[68,76],"expression.":[69],"Different":[70],"combinations":[71],"expression":[77,179],"generate":[79],"diverse":[80],"text":[81],"descriptions.":[82],"Additionally,":[83],"these":[84,95],"exhibit":[86],"variations":[87],"resolution,":[89,192],"color,":[90,193],"perspective.":[92],"To":[93],"address":[94,198],"challenges,":[96],"this":[97,211],"paper":[98,212],"proposes":[99,213],"multi-task":[101],"guided":[102],"fusion":[103,110,205],"encoder":[104],"(MTGFE)":[105],"based":[106],"on":[107,231],"multimodal":[109],"encoding":[111],"method,":[112,217,239],"progressiveness":[114],"which":[116,218],"proved":[119],"natural":[125],"images.":[126],"By":[127],"jointly":[128],"training":[129],"model":[131],"with":[132,188,203],"three":[133],"tasks:":[134],"matching":[136],"(ITM),":[137],"masked":[138],"language":[139],"modeling":[140],"(MLM),":[141],"newly":[144],"introduced":[145],"multi-view":[146],"joint":[147,177],"representations":[148],"contrast":[149],"(MVJRC),":[150],"we":[151],"enhance":[152],"its":[153,244],"capability":[154],"capture":[156],"fine-grained":[157,181],"correlations":[158],"between":[159],"texts.":[164],"Specifically,":[165],"MVJRC":[167],"is":[169],"designed":[170],"improve":[172,208],"model\u2019s":[174],"consistency":[175],"representation":[178],"correlation,":[182],"particularly":[183],"for":[184],"differences":[190],"angle.":[195],"Furthermore,":[196],"computational":[200],"complexity":[201],"associated":[202],"large-scale":[204],"models":[206],"efficiency,":[210],"filtering":[216],"achieves":[219],"higher":[220],"efficiency":[222],"while":[223],"minimizing":[224],"accuracy":[225],"loss.":[226],"Extensive":[227],"experiments":[228],"were":[229],"conducted":[230],"four":[232],"public":[233],"datasets":[234],"evaluate":[236],"proposed":[238],"results":[242],"validate":[243],"effectiveness.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2023-09-22T00:00:00"}