{"id":"https://openalex.org/W4372260352","doi":"https://doi.org/10.1109/icassp49357.2023.10096655","title":"MMCosine: Multi-Modal Cosine Loss Towards Balanced Audio-Visual Fine-Grained Learning","display_name":"MMCosine: Multi-Modal Cosine Loss Towards Balanced Audio-Visual Fine-Grained Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260352","doi":"https://doi.org/10.1109/icassp49357.2023.10096655"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113148426","display_name":"Ruize Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruize Xu","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052644412","display_name":"Ruoxuan Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoxuan Feng","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056567731","display_name":"Shixiong Zhang","orcid":"https://orcid.org/0000-0002-0314-9199"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi-Xiong Zhang","raw_affiliation_strings":["Tencent AI Lab,Bellevue,WA,USA","Tencent AI Lab, Bellevue, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100670614","display_name":"Di Hu","orcid":"https://orcid.org/0000-0002-7118-6733"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Hu","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9940000176429749,"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/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.7578454613685608},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7277026176452637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7224132418632507},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6335937976837158},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6335568428039551},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6172163486480713},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5507251024246216},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48609137535095215},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.47033482789993286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4579429030418396},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4536449909210205},{"id":"https://openalex.org/keywords/trigonometric-functions","display_name":"Trigonometric functions","score":0.446232408285141},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3365088403224945},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1320885419845581},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08172282576560974}],"concepts":[{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.7578454613685608},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7277026176452637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224132418632507},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6335937976837158},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6335568428039551},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6172163486480713},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5507251024246216},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48609137535095215},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.47033482789993286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4579429030418396},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4536449909210205},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.446232408285141},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3365088403224945},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1320885419845581},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08172282576560974},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2726515241","https://openalex.org/W2741447225","https://openalex.org/W2760103357","https://openalex.org/W2787873795","https://openalex.org/W2808631503","https://openalex.org/W2916104401","https://openalex.org/W2962788625","https://openalex.org/W2962898354","https://openalex.org/W2963656735","https://openalex.org/W2969985801","https://openalex.org/W2972986505","https://openalex.org/W3034552680","https://openalex.org/W3035180180","https://openalex.org/W3035333188","https://openalex.org/W3096936581","https://openalex.org/W3163527109","https://openalex.org/W3174906557","https://openalex.org/W3182707920","https://openalex.org/W4206237889","https://openalex.org/W4240805545","https://openalex.org/W4286750570","https://openalex.org/W4292958273","https://openalex.org/W4293478066","https://openalex.org/W4301785137","https://openalex.org/W4312242460","https://openalex.org/W4312639100","https://openalex.org/W6728271538","https://openalex.org/W6735013348","https://openalex.org/W6797613833","https://openalex.org/W6804138277","https://openalex.org/W6841484515","https://openalex.org/W6842019321"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W126212742","https://openalex.org/W1948687848","https://openalex.org/W2953417386","https://openalex.org/W2473504045","https://openalex.org/W875509673","https://openalex.org/W4313413039","https://openalex.org/W3182441879","https://openalex.org/W2619127353"],"abstract_inverted_index":{"Audio-visual":[0],"learning":[1],"helps":[2],"to":[3,33,95],"comprehensively":[4],"under-stand":[5],"the":[6,20,35,42,63,113,117,125,128,134,140],"world":[7],"by":[8,62],"fusing":[9],"practical":[10],"information":[11],"from":[12,116],"multiple":[13],"modalities.":[14],"However,":[15],"recent":[16],"studies":[17],"show":[18],"that":[19,41,68,108],"imbalanced":[21,114],"optimization":[22,115],"of":[23,65,119,127,136],"uni-modal":[24],"encoders":[25],"in":[26],"a":[27,31,54,88],"joint-learning":[28],"model":[29],"is":[30,154],"bottleneck":[32],"enhancing":[34],"model\u2019s":[36],"performance.":[37],"We":[38,106],"further":[39],"find":[40],"up-to-date":[43,148],"imbalance-mitigating":[44,149],"methods":[45],"fail":[46],"on":[47],"some":[48],"audio-visual":[49],"fine-grained":[50,104],"tasks,":[51],"which":[52],"have":[53],"higher":[55],"demand":[56],"for":[57],"distinguishable":[58],"feature":[59,71],"distribution.":[60],"Fueled":[61],"success":[64],"cosine":[66,129],"loss":[67],"builds":[69],"hyperspherical":[70],"spaces":[72],"and":[73,97,101,122,139,147],"achieves":[74],"lower":[75],"intra-class":[76],"angular":[77],"variability,":[78],"this":[79],"paper":[80],"proposes":[81],"Multi-Modal":[82],"Cosine":[83],"loss,":[84],"MMCosine.":[85],"It":[86],"performs":[87],"modality-wise":[89],"L":[90],"<inf":[91],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</inf>":[93],"normalization":[94],"features":[96],"weights":[98],"towards":[99],"balanced":[100],"better":[102],"multi-modal":[103,144],"learning.":[105],"demonstrate":[107],"our":[109,137],"method":[110,138],"can":[111],"alleviate":[112],"perspective":[118],"weight":[120],"norm":[121],"fully":[123],"exploit":[124],"discriminability":[126],"metric.":[130],"Extensive":[131],"experiments":[132],"prove":[133],"effectiveness":[135],"versatility":[141],"with":[142],"advanced":[143],"fusion":[145],"strategies":[146],"methods.":[150],"The":[151],"project":[152],"page":[153],"https://gewu-lab.github.io/MMCosine/.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}