{"id":"https://openalex.org/W4389386424","doi":"https://doi.org/10.1145/3636427","title":"CMAF: Cross-Modal Augmentation via Fusion for Underwater Acoustic Image Recognition","display_name":"CMAF: Cross-Modal Augmentation via Fusion for Underwater Acoustic Image Recognition","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4389386424","doi":"https://doi.org/10.1145/3636427"},"language":"en","primary_location":{"id":"doi:10.1145/3636427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3636427","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5101704895","display_name":"Shih\u2010Wei Yang","orcid":"https://orcid.org/0009-0009-6949-2609"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih-Wei Yang","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Taiwan","Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":"https://orcid.org/0009-0009-6949-2609","affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019371571","display_name":"Li-Hsiang Shen","orcid":"https://orcid.org/0000-0002-6412-5457"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Hsiang Shen","raw_affiliation_strings":["National Central University, Taiwan","Department of Communication Engineering National Central University, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-6412-5457","affiliations":[{"raw_affiliation_string":"National Central University, Taiwan","institution_ids":["https://openalex.org/I22265921"]},{"raw_affiliation_string":"Department of Communication Engineering National Central University, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040050806","display_name":"Hong-Han Shuai","orcid":"https://orcid.org/0000-0003-2216-077X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hong-Han Shuai","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Taiwan","Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-2216-077X","affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020169858","display_name":"Kai\u2010Ten Feng","orcid":"https://orcid.org/0000-0002-2781-8449"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai-Ten Feng","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Taiwan","Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-2781-8449","affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0621,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8917877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"20","issue":"5","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9815000295639038,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9815000295639038,"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"}},{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.98089998960495,"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"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.9790999889373779,"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":0.7534599304199219},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.7460072636604309},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6971838474273682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6522753834724426},{"id":"https://openalex.org/keywords/sonar","display_name":"Sonar","score":0.6058086156845093},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6011072397232056},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5382551550865173},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5010921955108643},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5002460479736328},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.4913906157016754},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4727369546890259},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43414804339408875},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4175402820110321},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4092187285423279},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08144381642341614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534599304199219},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.7460072636604309},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6971838474273682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6522753834724426},{"id":"https://openalex.org/C555745239","wikidata":"https://www.wikidata.org/wiki/Q133220","display_name":"Sonar","level":2,"score":0.6058086156845093},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6011072397232056},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5382551550865173},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5010921955108643},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5002460479736328},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.4913906157016754},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4727369546890259},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43414804339408875},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4175402820110321},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4092187285423279},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08144381642341614},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3636427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3636427","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1551284826","https://openalex.org/W1686810756","https://openalex.org/W1993965912","https://openalex.org/W2000091035","https://openalex.org/W2008039491","https://openalex.org/W2017290684","https://openalex.org/W2020781692","https://openalex.org/W2081178814","https://openalex.org/W2098344006","https://openalex.org/W2104068357","https://openalex.org/W2107989834","https://openalex.org/W2129879516","https://openalex.org/W2135547085","https://openalex.org/W2148143831","https://openalex.org/W2767106145","https://openalex.org/W2768267620","https://openalex.org/W2897327260","https://openalex.org/W2922054794","https://openalex.org/W2946165673","https://openalex.org/W2952448206","https://openalex.org/W2956232138","https://openalex.org/W2962865004","https://openalex.org/W2963435138","https://openalex.org/W2971495930","https://openalex.org/W2990176100","https://openalex.org/W2997763120","https://openalex.org/W3011751903","https://openalex.org/W3015967287","https://openalex.org/W3024771345","https://openalex.org/W3037998842","https://openalex.org/W3040835882","https://openalex.org/W3140428646","https://openalex.org/W3162090017","https://openalex.org/W3171662571","https://openalex.org/W3181199966","https://openalex.org/W3186165834","https://openalex.org/W3209760397","https://openalex.org/W4210355273","https://openalex.org/W4210407519","https://openalex.org/W4214503032","https://openalex.org/W4214865104","https://openalex.org/W4226206782","https://openalex.org/W4281777098","https://openalex.org/W4285108857","https://openalex.org/W4286652939","https://openalex.org/W4292977151","https://openalex.org/W4301366326","https://openalex.org/W4302275239","https://openalex.org/W4304014288","https://openalex.org/W4320487943","https://openalex.org/W4386076325","https://openalex.org/W6785809283"],"related_works":["https://openalex.org/W3199220297","https://openalex.org/W2137769200","https://openalex.org/W2070821970","https://openalex.org/W2032962400","https://openalex.org/W2952608638","https://openalex.org/W1996172652","https://openalex.org/W2911323905","https://openalex.org/W56094667","https://openalex.org/W2350761455","https://openalex.org/W2505159293"],"abstract_inverted_index":{"Underwater":[0],"image":[1,23,35,77],"recognition":[2],"is":[3,51,146],"crucial":[4],"for":[5,44,74],"underwater":[6,45,49],"detection":[7],"applications.":[8],"Fish":[9],"classification":[10,24,36],"has":[11],"been":[12],"one":[13],"of":[14,127],"the":[15,83,95,104,125,132,140],"emerging":[16],"research":[17],"areas":[18],"in":[19],"recent":[20],"years.":[21],"Existing":[22],"models":[25,37],"usually":[26],"classify":[27],"data":[28,41,50],"collected":[29],"from":[30],"terrestrial":[31,40],"environments.":[32],"However,":[33],"existing":[34],"trained":[38],"with":[39,118],"are":[42],"unsuitable":[43],"images,":[46],"as":[47],"identifying":[48],"challenging":[52],"due":[53],"to":[54,123],"their":[55],"incomplete":[56],"and":[57,90,112,130],"noisy":[58],"features.":[59],"To":[60],"address":[61,131],"this,":[62],"we":[63],"propose":[64],"a":[65,98,114,119],"cross-modal":[66],"augmentation":[67],"via":[68],"fusion":[69,110],"(":[70],"CMAF":[71],")":[72],"framework":[73],"acoustic-based":[75],"fish":[76],"classification.":[78],"Our":[79,136,143],"approach":[80],"involves":[81],"separating":[82],"process":[84],"into":[85],"two":[86],"branches:":[87],"visual":[88,105],"modality":[89],"sonar":[91],"signal":[92],"modality,":[93,106],"where":[94],"latter":[96],"provides":[97],"complementary":[99],"character":[100],"feature.":[101],"We":[102],"augment":[103],"design":[107],"an":[108],"attention-based":[109],"module,":[111],"adopt":[113],"masking-based":[115],"training":[116],"strategy":[117],"mask-based":[120],"focal":[121],"loss":[122],"improve":[124],"learning":[126],"local":[128],"features":[129],"class":[133],"imbalance":[134],"problem.":[135],"proposed":[137],"method":[138],"outperforms":[139],"state-of-the-art":[141],"methods.":[142],"source":[144],"code":[145],"available":[147],"at":[148],"https://github.com/WilkinsYang/CMAF":[149],".":[150]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
