{"id":"https://openalex.org/W4395029188","doi":"https://doi.org/10.1109/tgrs.2024.3392779","title":"Direction-Oriented Visual\u2013Semantic Embedding Model for Remote Sensing Image\u2013Text Retrieval","display_name":"Direction-Oriented Visual\u2013Semantic Embedding Model for Remote Sensing Image\u2013Text Retrieval","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4395029188","doi":"https://doi.org/10.1109/tgrs.2024.3392779"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3392779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3392779","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/A5101571340","display_name":"Qing Ma","orcid":"https://orcid.org/0000-0003-1749-9509"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qing Ma","raw_affiliation_strings":["College of Science, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1749-9509","affiliations":[{"raw_affiliation_string":"College of Science, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060268420","display_name":"Jiancheng Pan","orcid":"https://orcid.org/0000-0001-5968-5209"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiancheng Pan","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5968-5209","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013768600","display_name":"Cong Bai","orcid":"https://orcid.org/0000-0002-6177-3862"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Bai","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6177-3862","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101571340"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":8.8388,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.98557329,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"14"},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9993000030517578,"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":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.7374550104141235},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6694720387458801},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5602260828018188},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5197327136993408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5082261562347412},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.4730973541736603},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47019538283348083},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4591365158557892},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41964587569236755},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3946537971496582},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.1636686623096466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7374550104141235},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6694720387458801},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5602260828018188},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5197327136993408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5082261562347412},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.4730973541736603},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47019538283348083},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4591365158557892},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41964587569236755},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3946537971496582},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.1636686623096466}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2024.3392779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3392779","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/G389909570","display_name":null,"funder_award_id":"62102365","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G491842903","display_name":null,"funder_award_id":"61976192","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":60,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1485981043","https://openalex.org/W1522301498","https://openalex.org/W1905882502","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2111809230","https://openalex.org/W2112796928","https://openalex.org/W2133564696","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2401246392","https://openalex.org/W2515866431","https://openalex.org/W2546696630","https://openalex.org/W2774267535","https://openalex.org/W2779054585","https://openalex.org/W2890166583","https://openalex.org/W2898008292","https://openalex.org/W2962749812","https://openalex.org/W2962964995","https://openalex.org/W2963037989","https://openalex.org/W2964015378","https://openalex.org/W2964979676","https://openalex.org/W2990571534","https://openalex.org/W2994818707","https://openalex.org/W3004137323","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3092820619","https://openalex.org/W3100245404","https://openalex.org/W3105577662","https://openalex.org/W3140792177","https://openalex.org/W3154766321","https://openalex.org/W3155230099","https://openalex.org/W3165084071","https://openalex.org/W3190055600","https://openalex.org/W3198298840","https://openalex.org/W3208803664","https://openalex.org/W3217792975","https://openalex.org/W4210884681","https://openalex.org/W4221167444","https://openalex.org/W4224911357","https://openalex.org/W4283805294","https://openalex.org/W4284698859","https://openalex.org/W4284896388","https://openalex.org/W4292968451","https://openalex.org/W4296079338","https://openalex.org/W4312808420","https://openalex.org/W4313021481","https://openalex.org/W4379806246","https://openalex.org/W4385413432","https://openalex.org/W4386952228","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6679434410","https://openalex.org/W6726873649","https://openalex.org/W6747225742","https://openalex.org/W6809938868","https://openalex.org/W7057556061"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2312145515","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"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1],"has":[2],"developed":[3],"rapidly":[4],"in":[5,14,62,94],"recent":[6],"years.":[7],"However,":[8],"it":[9],"is":[10,55,112],"still":[11],"a":[12,38,72,78,105,135],"challenge":[13],"remote":[15],"sensing":[16],"due":[17],"to":[18,23,45,56,71,114,139],"visual-semantic":[19,137],"imbalance,":[20],"which":[21],"leads":[22],"incorrect":[24],"matching":[25],"of":[26,118,161],"non-semantic":[27],"visual":[28,58,75,90,102,142,153,177],"and":[29,51,59,91,122,144,154,159,176,184],"textual":[30,60,92,120,155],"features.":[31,103],"To":[32],"solve":[33],"this":[34],"problem,":[35],"we":[36,133],"propose":[37],"novel":[39],"Direction-Oriented":[40],"Visual-semantic":[41],"Embedding":[42],"Model":[43],"(DOVE)":[44],"mine":[46],"the":[47,85,88,95,116,151],"relationship":[48],"between":[49,87],"vision":[50],"language.":[52],"Our":[53],"highlight":[54],"conduct":[57],"representations":[61],"latent":[63,96],"space,":[64,98],"directing":[65],"them":[66],"as":[67,69,146],"close":[68],"possible":[70],"redundancy-free":[73],"regional":[74,101],"representation.":[76],"Concretely,":[77],"Regional-Oriented":[79],"Attention":[80],"Module":[81],"(ROAM)":[82],"adaptively":[83],"adjusts":[84],"distance":[86],"final":[89,152],"embeddings":[93],"semantic":[97,126],"oriented":[99],"by":[100,166],"Meanwhile,":[104],"lightweight":[106],"Digging":[107],"Text":[108],"Genome":[109],"Assistant":[110],"(DTGA)":[111],"designed":[113],"expand":[115],"range":[117],"tractable":[119],"representation":[121],"enhance":[123],"global":[124,136],"word-level":[125],"connections":[127],"using":[128],"less":[129],"attention":[130],"operations.":[131],"Ultimately,":[132],"exploit":[134],"constraint":[138,149],"reduce":[140],"single":[141],"dependency":[143],"serve":[145],"an":[147],"external":[148],"for":[150],"representations.":[156],"The":[157],"effectiveness":[158],"superiority":[160],"our":[162],"method":[163],"are":[164],"verified":[165],"extensive":[167],"experiments":[168],"including":[169],"parameter":[170],"evaluation,":[171],"quantitative":[172],"comparison,":[173],"ablation":[174],"studies":[175],"analysis,":[178],"on":[179],"two":[180],"benchmark":[181],"datasets,":[182],"RSICD":[183],"RSITMD.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":7}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}