{"id":"https://openalex.org/W4405270427","doi":"https://doi.org/10.1109/tgrs.2024.3515171","title":"Constructing a Multi-Modal Based Underwater Acoustic Target Recognition Method With a Pre-Trained Language-Audio Model","display_name":"Constructing a Multi-Modal Based Underwater Acoustic Target Recognition Method With a Pre-Trained Language-Audio Model","publication_year":2024,"publication_date":"2024-12-11","ids":{"openalex":"https://openalex.org/W4405270427","doi":"https://doi.org/10.1109/tgrs.2024.3515171"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2024.3515171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3515171","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/A5102609868","display_name":"Bowen Fu","orcid":"https://orcid.org/0000-0002-2167-4341"},"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":"Bowen Fu","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","School of Computer Science, Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-2167-4341","affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025506983","display_name":"Jiangtao Nie","orcid":"https://orcid.org/0000-0003-3692-6545"},"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":"Jiangtao Nie","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","School of Computer Science, Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-3692-6545","affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323672","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-0655-056X"},"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":"Wei Wei","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","School of Computer Science, Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-0655-056X","affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433957","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-7528-420X"},"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":"Lei Zhang","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","School of Computer Science, Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-7528-420X","affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":2.177,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8721218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9596999883651733,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9596999883651733,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7006714344024658},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.6744013428688049},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5960044860839844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.50718092918396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4143667221069336},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3255775272846222},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.18825647234916687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006714344024658},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.6744013428688049},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5960044860839844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.50718092918396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4143667221069336},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3255775272846222},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.18825647234916687},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2024.3515171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2024.3515171","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":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G151933513","display_name":null,"funder_award_id":"62101454","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3420112582","display_name":null,"funder_award_id":"62372379","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3820912390","display_name":null,"funder_award_id":"24ZDCYJSGG0003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5981921176","display_name":null,"funder_award_id":"62472359","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7591048978","display_name":"\u8054\u5408\u6df1\u5ea6\u5148\u9a8c\u548c\u9000\u5316\u8fc7\u7a0b\u5efa\u6a21\u7684\u9ad8\u5149\u8c31\u56fe\u50cf\u76f2\u8d85\u5206\u8fa8\u91cd\u5efa\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62071387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8160680875","display_name":null,"funder_award_id":"20240019053004","funder_id":"https://openalex.org/F4320322857","funder_display_name":"Aeronautical Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322857","display_name":"Aeronautical Science Foundation of China","ror":"https://ror.org/02wq41p38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1556884246","https://openalex.org/W2140010911","https://openalex.org/W2162005634","https://openalex.org/W2194775991","https://openalex.org/W2466903746","https://openalex.org/W2593116425","https://openalex.org/W2768531411","https://openalex.org/W2792643794","https://openalex.org/W2905385593","https://openalex.org/W2920164921","https://openalex.org/W2982407353","https://openalex.org/W2997819422","https://openalex.org/W3042565971","https://openalex.org/W3092682343","https://openalex.org/W3093961233","https://openalex.org/W3118765838","https://openalex.org/W3132949086","https://openalex.org/W3135247824","https://openalex.org/W3157467987","https://openalex.org/W3172124183","https://openalex.org/W3176445421","https://openalex.org/W3185341429","https://openalex.org/W3197875779","https://openalex.org/W3198811334","https://openalex.org/W3206645997","https://openalex.org/W4213143559","https://openalex.org/W4225630686","https://openalex.org/W4226442948","https://openalex.org/W4284898017","https://openalex.org/W4292970430","https://openalex.org/W4303712167","https://openalex.org/W4307964330","https://openalex.org/W4309627742","https://openalex.org/W4312443924","https://openalex.org/W4312956471","https://openalex.org/W4319970148","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4380785071","https://openalex.org/W4385408259","https://openalex.org/W4386076681","https://openalex.org/W4386790226","https://openalex.org/W4386821590","https://openalex.org/W4386973172","https://openalex.org/W4387672464","https://openalex.org/W4388240219","https://openalex.org/W4388739300","https://openalex.org/W4390510266","https://openalex.org/W4391432318","https://openalex.org/W4391642537","https://openalex.org/W4402670135","https://openalex.org/W6732646663","https://openalex.org/W6754473786","https://openalex.org/W6791353385","https://openalex.org/W6799174933","https://openalex.org/W6851629679","https://openalex.org/W6852818750"],"related_works":["https://openalex.org/W4388412763","https://openalex.org/W1999583034","https://openalex.org/W3168963531","https://openalex.org/W2591930867","https://openalex.org/W2953138830","https://openalex.org/W2773822314","https://openalex.org/W232178625","https://openalex.org/W623742799","https://openalex.org/W4248064953","https://openalex.org/W4311789548"],"abstract_inverted_index":{"Underwater":[0],"acoustic":[1,10,34,69],"target":[2,240],"recognition":[3,95,180,241],"(UATR)":[4],"aims":[5],"to":[6,26,65,122,156],"accurately":[7],"identify":[8],"radiated":[9],"signals":[11,51,70],"from":[12,30,68],"ships":[13],"in":[14,24,168,194],"complex":[15,31],"maritime":[16],"environments.":[17],"The":[18],"challenges":[19],"of":[20,115],"this":[21,133],"task":[22,211],"lay":[23],"how":[25],"explore":[27],"discriminative":[28],"representation":[29,62,85],"and":[32,78,87,112,125,150,159,172,221,231,245],"limited":[33,83,192],"samples.":[35],"Recently,":[36],"various":[37],"deep":[38],"learning-based":[39,152],"UATR":[40,138,199,209],"methods":[41,58],"have":[42],"been":[43],"proposed.":[44,203],"However,":[45,81],"their":[46],"performance":[47,96,124,242],"on":[48,226],"real":[49],"sonar-collected":[50],"remains":[52],"restricted.":[53],"On":[54,98],"one":[55],"hand,":[56,101],"most":[57],"currently":[59],"adopt":[60],"different":[61],"extraction":[63,114],"strategies":[64,91],"extract":[66],"features":[67,177],"such":[71],"as":[72],"time-frequency":[73],"(T-F)":[74],"representation,":[75,77],"wave":[76],"joint":[79],"representation.":[80],"the":[82,94,99,105,113,166,173,187,207,235],"feature":[84,89],"capability":[86],"simple":[88],"fusion":[90,154],"often":[92,103],"limit":[93],"improvement.":[97],"other":[100],"they":[102],"overlook":[104],"knowledge":[106,171],"gains":[107],"brought":[108],"by":[109,212],"pre-trained":[110,147,222],"models":[111],"multifeature":[116,137],"semantic":[117,174,218],"correlation":[118],"knowledge.":[119],"This":[120,163],"leads":[121],"unsatisfactory":[123],"even":[126],"overfitting":[127],"issues.":[128],"To":[129],"mitigate":[130],"these":[131],"issues,":[132],"article":[134],"proposes":[135],"a":[136,143,196],"(MF-UATR)":[139],"method.":[140],"It":[141,204],"introduces":[142],"strongly":[144],"generalized":[145],"multi-modal":[146,197],"language-audio":[148],"model":[149,167],"contrastive":[151],"feature-level":[153],"strategy":[155,164],"semantically":[157],"guide":[158],"fuse":[160],"multiple":[161],"features.":[162],"facilitates":[165],"learning":[169],"prior":[170],"correlations":[175],"between":[176],"thereby":[178],"improving":[179],"performance.":[181],"In":[182],"addition,":[183],"we":[184],"also":[185],"considered":[186],"few-shot":[188,198,208,246],"scenarios":[189],"with":[190],"extremely":[191],"data,":[193],"which":[195],"(MMFS-UATR)":[200],"scheme":[201],"is":[202],"efficiently":[205],"completes":[206],"(FS-UATR)":[210],"combining":[213],"parameter-efficient":[214],"fine-tuning":[215],"(PEFT)":[216],"techniques,":[217],"supervision":[219],"strategy,":[220],"MF-UATR.":[223],"Extensive":[224],"experiments":[225],"two":[227],"public":[228],"datasets,":[229],"DeepShip":[230],"ShipsEar,":[232],"demonstrate":[233],"that":[234],"proposed":[236],"frameworks":[237],"achieve":[238],"optimal":[239],"under":[243],"regular":[244],"settings.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}