{"id":"https://openalex.org/W4399731583","doi":"https://doi.org/10.3390/rs16122201","title":"An Enhanced Feature Extraction Framework for Cross-Modal Image\u2013Text Retrieval","display_name":"An Enhanced Feature Extraction Framework for Cross-Modal Image\u2013Text Retrieval","publication_year":2024,"publication_date":"2024-06-17","ids":{"openalex":"https://openalex.org/W4399731583","doi":"https://doi.org/10.3390/rs16122201"},"language":"en","primary_location":{"id":"doi:10.3390/rs16122201","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16122201","pdf_url":"https://www.mdpi.com/2072-4292/16/12/2201/pdf?version=1718671975","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/2072-4292/16/12/2201/pdf?version=1718671975","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101427440","display_name":"Jinzhi Zhang","orcid":"https://orcid.org/0000-0001-6430-0502"},"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":"Jinzhi Zhang","raw_affiliation_strings":["School of Information and Communication, National University of Defense Technology, Wuhan 430030, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430030, 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 430030, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430030, 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 430030, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430030, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100623941","display_name":"Xu Wang","orcid":"https://orcid.org/0000-0003-0803-2229"},"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 430030, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430030, 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 430030, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, National University of Defense Technology, Wuhan 430030, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.735,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70373942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"16","issue":"12","first_page":"2201","last_page":"2201"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"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":0.6328495740890503},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6130786538124084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5127006769180298},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44621142745018005},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4258251190185547},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3478265404701233},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3383452296257019},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.12600132822990417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6328495740890503},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6130786538124084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5127006769180298},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44621142745018005},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4258251190185547},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3478265404701233},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3383452296257019},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.12600132822990417},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/rs16122201","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16122201","pdf_url":"https://www.mdpi.com/2072-4292/16/12/2201/pdf?version=1718671975","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:9832cd1c645844958c2bea583b0bc857","is_oa":true,"landing_page_url":"https://doaj.org/article/9832cd1c645844958c2bea583b0bc857","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 16, Iss 12, p 2201 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/rs16122201","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16122201","pdf_url":"https://www.mdpi.com/2072-4292/16/12/2201/pdf?version=1718671975","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":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[{"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"}],"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/W4399731583.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2779054585","https://openalex.org/W2964120214","https://openalex.org/W3004137323","https://openalex.org/W3100245404","https://openalex.org/W3111501160","https://openalex.org/W3140792177","https://openalex.org/W3165084071","https://openalex.org/W3208803664","https://openalex.org/W3217792975","https://openalex.org/W4224911357","https://openalex.org/W4283721482","https://openalex.org/W4286630479","https://openalex.org/W4292070612","https://openalex.org/W4311002506","https://openalex.org/W4312219282","https://openalex.org/W4312272363","https://openalex.org/W4313160444","https://openalex.org/W4317631456","https://openalex.org/W4323338969","https://openalex.org/W4376109647","https://openalex.org/W4381790494","https://openalex.org/W4382699376","https://openalex.org/W4384073069","https://openalex.org/W4384563036","https://openalex.org/W4387617598","https://openalex.org/W6802704712","https://openalex.org/W6804635132","https://openalex.org/W6810559079"],"related_works":["https://openalex.org/W2601157893","https://openalex.org/W2131735617","https://openalex.org/W2373006798","https://openalex.org/W2056912418","https://openalex.org/W2123759770","https://openalex.org/W2033213769","https://openalex.org/W4312376745","https://openalex.org/W2136016640","https://openalex.org/W2082269393","https://openalex.org/W2043960970"],"abstract_inverted_index":{"In":[0,8],"general,":[1],"remote":[2,13],"sensing":[3,14],"images":[4],"depict":[5],"intricate":[6],"scenes.":[7],"cross-modal":[9],"retrieval":[10,191],"tasks":[11,192],"involving":[12,193],"images,":[15],"the":[16,34,44,71,81,116,130,156,177],"accompanying":[17],"text":[18],"includes":[19],"numerus":[20],"information":[21,52,84],"with":[22],"an":[23],"emphasis":[24],"on":[25,107,125,145],"mainly":[26],"large":[27,54,93,123],"objects":[28],"due":[29,89],"to":[30,59,86,90,119,135,175,187],"higher":[31],"attention,":[32],"and":[33,155,168,183],"features":[35,61,137],"from":[36,70,92,122,138],"small":[37,63,87,126,139,181],"targets":[38,64,88,124,182],"are":[39],"often":[40],"omitted":[41],"naturally.":[42],"While":[43],"conventional":[45],"vision":[46],"transformer":[47],"(ViT)":[48],"method":[49],"adeptly":[50],"captures":[51],"regarding":[53],"global":[55],"targets,":[56],"its":[57],"capability":[58],"extract":[60,136],"of":[62,83,132,166,180],"is":[65],"limited.":[66],"This":[67],"limitation":[68],"stems":[69],"constrained":[72],"receptive":[73,113],"field":[74],"in":[75,115,163],"ViT\u2019s":[76],"self-attention":[77],"layer,":[78],"which":[79,110],"hinders":[80],"extraction":[82],"pertaining":[85],"interference":[91,121],"targets.":[94,140],"To":[95],"address":[96],"this":[97,99],"concern,":[98],"study":[100],"introduces":[101],"a":[102],"patch":[103],"classification":[104],"framework":[105],"based":[106],"feature":[108,117],"similarity,":[109],"establishes":[111],"distinct":[112],"fields":[114],"space":[118],"mitigate":[120],"ones,":[127],"thereby":[128],"enhancing":[129],"ability":[131],"traditional":[133],"ViT":[134],"We":[141],"conducted":[142],"evaluation":[143],"experiments":[144],"two":[146],"popular":[147],"datasets\u2014the":[148],"Remote":[149,157],"Sensing":[150,158],"Image\u2013Text":[151],"Match":[152],"Dataset":[153,161],"(RSITMD)":[154],"Image":[159],"Captioning":[160],"(RSICD)\u2014resulting":[162],"mR":[164],"indices":[165],"35.6%":[167],"19.47%,":[169],"respectively.":[170],"The":[171],"proposed":[172],"approach":[173],"contributes":[174],"improving":[176],"detection":[178],"accuracy":[179],"can":[184],"be":[185],"applied":[186],"more":[188],"complex":[189],"image\u2013text":[190],"multi-scale":[194],"ground":[195],"objects.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}