{"id":"https://openalex.org/W4313154462","doi":"https://doi.org/10.1145/3556384.3556414","title":"Hierarchical Multi-modal Transformer for Automatic Detection of COVID-19","display_name":"Hierarchical Multi-modal Transformer for Automatic Detection of COVID-19","publication_year":2022,"publication_date":"2022-08-04","ids":{"openalex":"https://openalex.org/W4313154462","doi":"https://doi.org/10.1145/3556384.3556414"},"language":"en","primary_location":{"id":"doi:10.1145/3556384.3556414","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3556384.3556414","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3556384.3556414","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 5th International Conference on Signal Processing and Machine Learning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3556384.3556414","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037025716","display_name":"Shuyun Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shuyun Tang","raw_affiliation_strings":["Virufy AI Research, University of California, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Virufy AI Research, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102514528","display_name":"Xinying Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinying Hu","raw_affiliation_strings":["Virufy AI Research, University of California, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Virufy AI Research, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019670377","display_name":"Les Atlas","orcid":"https://orcid.org/0009-0001-9979-5864"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Les Atlas","raw_affiliation_strings":["University of Washington, USA"],"affiliations":[{"raw_affiliation_string":"University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010647585","display_name":"Amil Khanzada","orcid":"https://orcid.org/0000-0002-7065-5390"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amil Khanzada","raw_affiliation_strings":["Virufy AI Research, University of California, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Virufy AI Research, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001436196","display_name":"Mert Pilanc\u0131","orcid":"https://orcid.org/0000-0002-0870-9992"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mert Pilanci","raw_affiliation_strings":["Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037025716"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":1.155,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77595667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"197","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10654","display_name":"Pneumonia and Respiratory Infections","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9750999808311462,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8290737271308899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7552282214164734},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6287180185317993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5722652673721313},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5376182198524475},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46177801489830017},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4240490794181824},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36071884632110596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3478957414627075},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10714229941368103},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08221331238746643}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8290737271308899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7552282214164734},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6287180185317993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5722652673721313},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5376182198524475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46177801489830017},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4240490794181824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36071884632110596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3478957414627075},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10714229941368103},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08221331238746643},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3556384.3556414","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3556384.3556414","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3556384.3556414","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 5th International Conference on Signal Processing and Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3556384.3556414","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3556384.3556414","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3556384.3556414","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 5th International Conference on Signal Processing and Machine Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[{"id":"https://openalex.org/G1998373881","display_name":null,"funder_award_id":"2037304","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4864293789","display_name":null,"funder_award_id":"ECCS-2037304","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5346705942","display_name":null,"funder_award_id":"DMS-2134248","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5805234136","display_name":"Collaborative Research: Scalable Linear Algebra and Neural Network Theory","funder_award_id":"2134248","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313154462.pdf","grobid_xml":"https://content.openalex.org/works/W4313154462.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1924943994","https://openalex.org/W1986669541","https://openalex.org/W2148154194","https://openalex.org/W2511730936","https://openalex.org/W2512160354","https://openalex.org/W2964121744","https://openalex.org/W2964350391","https://openalex.org/W3013174866","https://openalex.org/W3028563376","https://openalex.org/W3045460727","https://openalex.org/W3092933647","https://openalex.org/W3095379519","https://openalex.org/W3135567124","https://openalex.org/W3196974791","https://openalex.org/W3201123210","https://openalex.org/W3205743929","https://openalex.org/W4221167107","https://openalex.org/W4283809036","https://openalex.org/W4287588084","https://openalex.org/W4310658768","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W2806259446","https://openalex.org/W2963326959","https://openalex.org/W4312407344","https://openalex.org/W1986582023","https://openalex.org/W2883749686","https://openalex.org/W2966829450","https://openalex.org/W4315864862"],"abstract_inverted_index":{"Automated":[0],"COVID-19":[1,143,158],"detection":[2],"based":[3],"on":[4,35,87,164],"analysis":[5],"of":[6,14,27,62,151],"cough":[7],"recordings":[8],"has":[9],"been":[10],"an":[11,131],"important":[12],"field":[13],"study,":[15],"as":[16,82],"efficient":[17,132],"and":[18,31,52,133,169],"accurate":[19,157],"methods":[20],"are":[21],"necessary":[22],"to":[23,54,64,71,91],"contain":[24],"the":[25,28,33,60,118,123,128,137,149],"spread":[26],"global":[29],"pandemic":[30],"relieve":[32],"burden":[34],"medical":[36],"facilities.":[37],"While":[38],"previous":[39,83],"works":[40,84],"presented":[41],"lightweight":[42],"machine":[43],"learning":[44],"models":[45,48],"[9],":[46],"these":[47,95],"may":[49],"sacrifice":[50],"accuracy":[51],"interpretability":[53],"integrate":[55],"into":[56],"mobile":[57],"devices.":[58],"Besides,":[59,122],"question":[61],"how":[63],"effectively":[65],"associate":[66],"indicators":[67],"from":[68,136],"audio":[69],"signals":[70],"other":[72],"modality":[73],"inputs":[74],"(i.e.":[75],"patient":[76],"information)":[77],"is":[78],"still":[79],"largely":[80],"unexplored,":[81],"predominantly":[85],"relied":[86],"simply":[88],"concatenated":[89],"features":[90],"learn.":[92],"To":[93],"tackle":[94],"issues,":[96],"this":[97],"paper":[98],"proposes":[99],"a":[100,113],"novel":[101],"Hierarchical":[102],"Multi-modal":[103],"Transformer":[104,140],"(HMT)":[105],"that":[106],"learns":[107],"more":[108,156],"informative":[109],"multi-modal":[110],"representations":[111],"with":[112],"cross":[114],"attention":[115],"module":[116],"during":[117],"feature":[119],"fusion":[120],"procedure.":[121],"block":[124],"aggregation":[125],"algorithm":[126],"for":[127,141,155],"HMT":[129],"provides":[130],"improved":[134],"solution":[135],"Vanilla":[138],"Vision":[139],"limited":[142],"benchmark":[144],"datasets.":[145],"Extensive":[146],"experiments":[147],"show":[148],"effectiveness":[150],"our":[152],"proposed":[153],"model":[154],"detection,":[159],"which":[160],"yield":[161],"state-of-the-art":[162],"results":[163],"two":[165],"public":[166],"datasets,":[167],"Coswara":[168],"COUGHVID.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}