{"id":"https://openalex.org/W3206187855","doi":"https://doi.org/10.1109/igarss47720.2021.9554533","title":"Cross-Modal Feature Fusion Retrieval for Remote Sensing Image-Voice Retrieval","display_name":"Cross-Modal Feature Fusion Retrieval for Remote Sensing Image-Voice Retrieval","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3206187855","doi":"https://doi.org/10.1109/igarss47720.2021.9554533","mag":"3206187855"},"language":"en","primary_location":{"id":"doi:10.1109/igarss47720.2021.9554533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss47720.2021.9554533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS","raw_type":"proceedings-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/A5030499511","display_name":"Rui Yang","orcid":"https://orcid.org/0000-0002-5634-5476"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yang","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749025","display_name":"Yu Gu","orcid":"https://orcid.org/0000-0003-3634-2275"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gu","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087012500","display_name":"Yu Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liao","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356963","display_name":"Huan Zhang","orcid":"https://orcid.org/0000-0002-5507-4985"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China","School of Journalism and Communication, Northwest University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Journalism and Communication, Northwest University, China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034670898","display_name":"Yingzhi Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingzhi Sun","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065660222","display_name":"Shuang Wang","orcid":"https://orcid.org/0000-0003-4940-1211"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Wang","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043022387","display_name":"Biao Hou","orcid":"https://orcid.org/0000-0002-1996-186X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Hou","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050630882","display_name":"Licheng Jiao","orcid":"https://orcid.org/0000-0003-3354-9617"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Licheng Jiao","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003201391","display_name":"He Zhang","orcid":"https://orcid.org/0000-0002-1832-8480"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China","School of Journalism and Communication, Northwest University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi'an, Shaanxi Province, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Journalism and Communication, Northwest University, China","institution_ids":["https://openalex.org/I37802460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2911,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.56765213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2855","last_page":"2858"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11309","display_name":"Music and Audio Processing","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9886000156402588,"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":0.8550589084625244},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6475229263305664},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6017085313796997},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5694764852523804},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5491427183151245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5471959114074707},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4611065983772278},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.44445550441741943},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42320311069488525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3604189455509186},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3414679765701294},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3201662600040436},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.31486037373542786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8550589084625244},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6475229263305664},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6017085313796997},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5694764852523804},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5491427183151245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5471959114074707},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4611065983772278},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.44445550441741943},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42320311069488525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3604189455509186},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3414679765701294},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3201662600040436},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31486037373542786},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igarss47720.2021.9554533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss47720.2021.9554533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5699999928474426,"display_name":"Reduced inequalities"},{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G570056697","display_name":null,"funder_award_id":"61771379","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":14,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2510520237","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2765440071","https://openalex.org/W2770954831","https://openalex.org/W2779054585","https://openalex.org/W2896457183","https://openalex.org/W2898008292","https://openalex.org/W2938495304","https://openalex.org/W2963341956","https://openalex.org/W3100245404","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W627697492","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/W2123991572"],"abstract_inverted_index":{"With":[0],"the":[1,26,54,90,97,103,122,136,140],"increasing":[2],"popularity":[3],"of":[4,15,29],"remote":[5,16,37,107,123],"sensing":[6,17,38,108,124],"technology":[7],"applications,":[8],"some":[9],"emergency":[10],"scenarios":[11],"require":[12],"rapid":[13],"retrieval":[14,40,72,91,126],"images,":[18],"such":[19],"as":[20],"earthquake":[21],"rescue,":[22],"etc.":[23],"Due":[24],"to":[25,102],"high":[27],"efficiency":[28],"voice":[30],"input,":[31],"researchers":[32],"have":[33,45],"focused":[34],"on":[35,131],"cross-modal":[36,69,80],"image-voice":[39,125],"methods.":[41],"However,":[42],"these":[43,63],"methods":[44],"two":[46,132],"major":[47],"drawbacks:":[48],"speech":[49],"input":[50],"lacks":[51],"discrimination":[52,120],"and":[53,87,117,139],"intra-modal":[55],"semantic":[56,119],"information":[57,101],"is":[58],"under":[59],"used.":[60],"To":[61],"address":[62],"drawbacks,":[64],"we":[65],"propose":[66],"a":[67,77],"novel":[68],"feature":[70,82,105],"fusion":[71],"model.":[73],"Our":[74],"model":[75,95,152],"provides":[76],"more":[78],"optimized":[79],"common":[81],"space":[83],"than":[84],"previous":[85],"models":[86,155],"thus":[88],"optimizes":[89],"performance.":[92],"First,":[93],"our":[94,151],"adds":[96],"extra":[98],"textual":[99],"keyword":[100],"audio":[104],"for":[106],"image":[109],"retrieval.":[110],"Second,":[111],"it":[112],"introduces":[113],"inter-modality":[114],"adversarial":[115],"learning":[116],"intra-modality":[118],"into":[121],"task.":[127,158],"We":[128],"conducted":[129],"experiments":[130],"datasets":[133],"modified":[134],"from":[135],"UCM-Captions":[137],"dataset":[138],"Remote":[141],"Sensing":[142],"Image":[143],"Caption":[144],"Dataset.":[145],"The":[146],"experimental":[147],"results":[148],"show":[149],"that":[150],"outperforms":[153],"state-of-the-art":[154],"in":[156],"this":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}