{"id":"https://openalex.org/W4408347332","doi":"https://doi.org/10.1109/icassp49660.2025.10889155","title":"Multi-label Recognition under Noisy Supervision: A Confusion Mixture Modeling Approach","display_name":"Multi-label Recognition under Noisy Supervision: A Confusion Mixture Modeling Approach","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347332","doi":"https://doi.org/10.1109/icassp49660.2025.10889155"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5084123460","display_name":"Diego Gonz\u00e1lez","orcid":"https://orcid.org/0000-0001-9154-270X"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diego Linares Gonzalez","raw_affiliation_strings":["University of Central Florida,Department of Electrical and Computer Engineering,Orlando,FL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida,Department of Electrical and Computer Engineering,Orlando,FL,USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005841750","display_name":"Shahana Ibrahim","orcid":"https://orcid.org/0000-0003-1951-5234"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shahana Ibrahim","raw_affiliation_strings":["University of Central Florida,Department of Electrical and Computer Engineering,Orlando,FL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida,Department of Electrical and Computer Engineering,Orlando,FL,USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":1.6508,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85013601,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.8823000192642212,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.8823000192642212,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8586999773979187,"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/confusion","display_name":"Confusion","score":0.805901288986206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7038636207580566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48607543110847473},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4077723026275635},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09176620841026306}],"concepts":[{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.805901288986206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7038636207580566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48607543110847473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4077723026275635},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09176620841026306},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1514928307","https://openalex.org/W1576514601","https://openalex.org/W1861492603","https://openalex.org/W2025666718","https://openalex.org/W2031489346","https://openalex.org/W2114315281","https://openalex.org/W2143890915","https://openalex.org/W2566079294","https://openalex.org/W2943963440","https://openalex.org/W2964292098","https://openalex.org/W2969792713","https://openalex.org/W2981873476","https://openalex.org/W3042609801","https://openalex.org/W3156331990","https://openalex.org/W3165691894","https://openalex.org/W3205749498","https://openalex.org/W4226013657","https://openalex.org/W4244259635","https://openalex.org/W4293409613","https://openalex.org/W4390874359","https://openalex.org/W4400654953","https://openalex.org/W6677082149","https://openalex.org/W6740005241","https://openalex.org/W6763576130","https://openalex.org/W6779482673","https://openalex.org/W6790117478"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2964976023","https://openalex.org/W1982477181","https://openalex.org/W2403083015","https://openalex.org/W4285488523","https://openalex.org/W2011367623","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Multi-label":[0],"recognition":[1],"is":[2,22,39],"a":[3,19,23,51,77,95,99,113,137],"critical":[4],"task":[5,25],"in":[6,15,58,87],"artificial":[7],"intelligence,":[8],"aiming":[9],"to":[10,47,102],"identify":[11],"every":[12],"object":[13],"present":[14],"an":[16,131],"image.":[17],"Designing":[18],"multi-label":[20,124,145],"classifier":[21,53],"nontrivial":[24],"both":[26],"from":[27],"data":[28],"collection":[29],"and":[30,42,68,107],"modeling":[31,67],"perspectives.":[32],"Collecting":[33],"multiple":[34],"labels":[35,64],"for":[36],"each":[37],"image":[38],"extremely":[40],"time-consuming":[41],"costly,":[43],"which":[44],"often":[45],"leads":[46],"noisy":[48,63],"annotations.":[49],"Furthermore,":[50],"robust":[52],"that":[54,82,140],"performs":[55],"reliably":[56],"well":[57],"the":[59,103,109,122,143,153],"presence":[60],"of":[61,115,155],"such":[62],"demands":[65],"meticulous":[66],"learning":[69,133],"criterion":[70,134],"design.":[71],"In":[72],"this":[73],"work,":[74],"we":[75,129],"propose":[76],"novel":[78],"probabilistic":[79],"confusion":[80,125],"model":[81,93],"effectively":[83,141],"incorporates":[84,94],"inter-label":[85],"interactions":[86],"causing":[88],"label":[89,104,110],"noise.":[90],"The":[91],"proposed":[92,123],"latent":[96],"variable,":[97],"building":[98],"hierarchical":[100],"structure":[101],"noise":[105,111],"generation,":[106],"represents":[108],"as":[112],"mixture":[114,126],"confusions":[116],"caused":[117],"by":[118],"various":[119,149],"classes.":[120],"Under":[121],"(MCM)":[127],"model,":[128],"design":[130],"end-to-end":[132],"along":[135],"with":[136,148],"sparsity":[138],"regularization,":[139],"estimates":[142],"true":[144],"classifier.":[146],"Experiments":[147],"real-world":[150],"datasets":[151],"showcase":[152],"effectiveness":[154],"our":[156],"approach.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}