{"id":"https://openalex.org/W4412445229","doi":"https://doi.org/10.1109/dsp65409.2025.11075076","title":"Improving Classification of Marine Mammal Vocalizations Using Vision Transformers and Phase-Related Features","display_name":"Improving Classification of Marine Mammal Vocalizations Using Vision Transformers and Phase-Related Features","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4412445229","doi":"https://doi.org/10.1109/dsp65409.2025.11075076"},"language":"en","primary_location":{"id":"doi:10.1109/dsp65409.2025.11075076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsp65409.2025.11075076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Digital Signal Processing (DSP)","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/A5072670448","display_name":"Dimitris N. Makropoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Dimitris N. Makropoulos","raw_affiliation_strings":["School of Electrical &#x0026; Computer Engineering, National Technical University of Athens,Greece"],"affiliations":[{"raw_affiliation_string":"School of Electrical &#x0026; Computer Engineering, National Technical University of Athens,Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025430640","display_name":"Panagiotis P. Filntisis","orcid":"https://orcid.org/0000-0002-2042-245X"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Panagiotis P. Filntisis","raw_affiliation_strings":["School of Electrical &#x0026; Computer Engineering, National Technical University of Athens,Greece"],"affiliations":[{"raw_affiliation_string":"School of Electrical &#x0026; Computer Engineering, National Technical University of Athens,Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073692690","display_name":"Aristides Prospathopoulos","orcid":"https://orcid.org/0000-0002-3150-6966"},"institutions":[{"id":"https://openalex.org/I4210131924","display_name":"Hellenic Centre for Marine Research","ror":"https://ror.org/038kffh84","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210131924"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Aristides Prospathopoulos","raw_affiliation_strings":["Institute of Oceanography,Hellenic Centre for Marine Research (HCMR),Greece"],"affiliations":[{"raw_affiliation_string":"Institute of Oceanography,Hellenic Centre for Marine Research (HCMR),Greece","institution_ids":["https://openalex.org/I4210131924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083789831","display_name":"Dimitris Kassis","orcid":"https://orcid.org/0000-0003-1373-7768"},"institutions":[{"id":"https://openalex.org/I4210131924","display_name":"Hellenic Centre for Marine Research","ror":"https://ror.org/038kffh84","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210131924"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitris Kassis","raw_affiliation_strings":["Institute of Oceanography,Hellenic Centre for Marine Research (HCMR),Greece"],"affiliations":[{"raw_affiliation_string":"Institute of Oceanography,Hellenic Centre for Marine Research (HCMR),Greece","institution_ids":["https://openalex.org/I4210131924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089203685","display_name":"Antigoni Tsiami","orcid":"https://orcid.org/0000-0001-9075-6343"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Antigoni Tsiami","raw_affiliation_strings":["School of Electrical &#x0026; Computer Engineering, National Technical University of Athens,Greece"],"affiliations":[{"raw_affiliation_string":"School of Electrical &#x0026; Computer Engineering, National Technical University of Athens,Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079243420","display_name":"Petros Maragos","orcid":"https://orcid.org/0000-0003-0534-2707"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Petros Maragos","raw_affiliation_strings":["School of Electrical &#x0026; Computer Engineering, National Technical University of Athens,Greece"],"affiliations":[{"raw_affiliation_string":"School of Electrical &#x0026; Computer Engineering, National Technical University of Athens,Greece","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5072670448"],"corresponding_institution_ids":["https://openalex.org/I174458059"],"apc_list":null,"apc_paid":null,"fwci":1.7776,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85542804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10659","display_name":"Marine animal studies overview","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10659","display_name":"Marine animal studies overview","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12596","display_name":"Cephalopods and Marine Biology","score":0.9613000154495239,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/marine-mammal","display_name":"Marine mammal","score":0.6742473840713501},{"id":"https://openalex.org/keywords/mammal","display_name":"Mammal","score":0.5859361886978149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5408987402915955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3528365194797516},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3329624533653259},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13932284712791443},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.12664976716041565}],"concepts":[{"id":"https://openalex.org/C2776384079","wikidata":"https://www.wikidata.org/wiki/Q382441","display_name":"Marine mammal","level":2,"score":0.6742473840713501},{"id":"https://openalex.org/C2778234026","wikidata":"https://www.wikidata.org/wiki/Q7377","display_name":"Mammal","level":2,"score":0.5859361886978149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5408987402915955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3528365194797516},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3329624533653259},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13932284712791443},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.12664976716041565}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsp65409.2025.11075076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsp65409.2025.11075076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2012771238","https://openalex.org/W2014893602","https://openalex.org/W2047789823","https://openalex.org/W2063487764","https://openalex.org/W2114537326","https://openalex.org/W2118864322","https://openalex.org/W2122787031","https://openalex.org/W2194775991","https://openalex.org/W2970226357","https://openalex.org/W3137493668","https://openalex.org/W3138516171","https://openalex.org/W3196683629","https://openalex.org/W4213019189","https://openalex.org/W4226051760","https://openalex.org/W4229921563","https://openalex.org/W4280640455","https://openalex.org/W4297775537","https://openalex.org/W4312349930","https://openalex.org/W4312591542","https://openalex.org/W4315767632","https://openalex.org/W4372260106","https://openalex.org/W4372262734","https://openalex.org/W4375869025","https://openalex.org/W4390060493","https://openalex.org/W4403447448","https://openalex.org/W4404577156","https://openalex.org/W6736723571","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2186967215","https://openalex.org/W2074055512","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407"],"abstract_inverted_index":{"In":[0,76,99],"this":[1,77],"study,":[2],"we":[3,27,79,105],"investigate":[4],"the":[5,56,107,113,117,146,180],"relative":[6],"performance":[7,135,158],"of":[8,42,103,109,148],"Vision":[9],"Transformers":[10,130,166],"(ViTs)":[11],"compared":[12],"to":[13,45,137,154],"convolution-based":[14,82,174],"neural":[15],"networks":[16,83,88],"in":[17],"categorizing":[18],"vocalizations":[19],"from":[20,33,71,112],"a":[21,39,100],"medium-sized":[22],"marine":[23,73],"mammal":[24,74],"dataset.":[25],"Additionally,":[26],"evaluate":[28],"whether":[29],"phase":[30,111,149],"information":[31,44],"derived":[32],"Fourier":[34,114],"decomposition":[35],"can":[36],"serve":[37],"as":[38,69],"complementary":[40],"source":[41],"useful":[43],"magnitude":[46,118],"for":[47,164,172,179],"classification":[48,170],"tasks.":[49],"Our":[50,120],"study":[51],"focuses":[52],"on":[53,94],"bioacoustics,":[54],"utilizing":[55],"publicly":[57],"available":[58],"Watkins":[59],"Marine":[60],"Mammal":[61],"Sound":[62],"Database,":[63],"which":[64],"contains":[65],"sound":[66],"clips":[67],"identified":[68],"originating":[70],"32":[72],"species.":[75],"framework,":[78],"first":[80],"trained":[81],"(ResNet-101,":[84],"MobileNetV3)":[85],"and":[86,133,144,167,175],"Transformer-based":[87],"(ViT":[89],"B-16,":[90],"Swin":[91,165],"Transformer":[92],"V2)":[93],"log-magnitude":[95],"spectrograms":[96,152],"(baseline":[97],"models).":[98],"second":[101],"set":[102],"experiments,":[104],"incorporated":[106],"derivative":[108],"unwrapped":[110],"representation":[115],"into":[116,151],"spectrograms.":[119],"results":[121],"show":[122],"that":[123],"(<tex":[124],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[125],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$a$</tex>)":[126],"Shifted":[127],"Window":[128],"(Swin)":[129],"outperform":[131],"MobileNets":[132],"achieve":[134],"similar":[136],"ResNets":[138],"while":[139],"maintaining":[140],"lower":[141],"computational":[142],"complexity":[143],"(b)":[145],"inclusion":[147],"derivatives":[150],"leads":[153],"(i)":[155],"consistently":[156],"improved":[157],"metrics":[159],"across":[160],"all":[161],"biosignal":[162],"categories":[163],"(ii)":[168],"enhanced":[169],"ability":[171],"both":[173],"self-attention-based":[176],"networks,":[177],"particularly":[178],"narrow-band":[181],"frequency":[182],"modulated":[183],"(FM)":[184],"whistles":[185],"emitted":[186],"by":[187],"delphinids,":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}