{"id":"https://openalex.org/W4308222712","doi":"https://doi.org/10.1145/3536221.3556581","title":"X-Norm: Exchanging Normalization Parameters for Bimodal Fusion","display_name":"X-Norm: Exchanging Normalization Parameters for Bimodal Fusion","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4308222712","doi":"https://doi.org/10.1145/3536221.3556581"},"language":"en","primary_location":{"id":"doi:10.1145/3536221.3556581","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3556581","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3556581","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal Interaction","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/10.1145/3536221.3556581","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028562848","display_name":"Yufeng Yin","orcid":"https://orcid.org/0000-0001-5558-2421"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yufeng Yin","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California, United States"],"raw_orcid":"https://orcid.org/0000-0001-5558-2421","affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California, United States","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089534818","display_name":"Jiashu Xu","orcid":"https://orcid.org/0000-0003-4093-2315"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiashu Xu","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California, United States"],"raw_orcid":"https://orcid.org/0000-0003-4093-2315","affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California, United States","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089696860","display_name":"Tianxin Zu","orcid":"https://orcid.org/0000-0002-8108-8889"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianxin Zu","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California, United States"],"raw_orcid":"https://orcid.org/0000-0002-8108-8889","affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California, United States","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024169758","display_name":"Mohammad Soleymani","orcid":"https://orcid.org/0000-0002-5873-1434"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Soleymani","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California, United States"],"raw_orcid":"https://orcid.org/0000-0002-5873-1434","affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California, United States","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028562848"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68923546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"605","last_page":"614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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/T12031","display_name":"Speech and dialogue systems","score":0.9955999851226807,"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/normalization","display_name":"Normalization (sociology)","score":0.8153038620948792},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6139910817146301},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.5222340822219849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4952150881290436},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4398963153362274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31187981367111206},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09053626656532288},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.06573718786239624}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8153038620948792},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6139910817146301},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.5222340822219849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4952150881290436},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4398963153362274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31187981367111206},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09053626656532288},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.06573718786239624},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3536221.3556581","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3556581","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3556581","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3536221.3556581","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3556581","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3556581","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308222712.pdf","grobid_xml":"https://content.openalex.org/works/W4308222712.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W22229905","https://openalex.org/W2032406331","https://openalex.org/W2108598243","https://openalex.org/W2309561466","https://openalex.org/W2342475039","https://openalex.org/W2470413457","https://openalex.org/W2603777577","https://openalex.org/W2610961739","https://openalex.org/W2753840835","https://openalex.org/W2760103357","https://openalex.org/W2890952074","https://openalex.org/W2936451900","https://openalex.org/W2937584914","https://openalex.org/W2963524571","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2969556441","https://openalex.org/W2979826702","https://openalex.org/W2997604315","https://openalex.org/W3015308237","https://openalex.org/W3016234935","https://openalex.org/W3021013305","https://openalex.org/W3034972874","https://openalex.org/W3035333188","https://openalex.org/W3093895424","https://openalex.org/W3100133290","https://openalex.org/W3116570699","https://openalex.org/W4210611093","https://openalex.org/W4301104990"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2353265673","https://openalex.org/W2152662039"],"abstract_inverted_index":{"Multimodal":[0,130],"learning":[1],"aims":[2],"to":[3,11,113],"process":[4],"and":[5,35,46,54,78,86,91,96,119,129],"relate":[6],"information":[7],"from":[8],"different":[9,82],"modalities":[10,63],"enhance":[12],"the":[13,26,62,66,114],"model\u2019s":[14],"capacity":[15],"for":[16,33,49,93,98],"perception.":[17],"Current":[18],"multimodal":[19],"fusion":[20,51],"mechanisms":[21],"either":[22],"do":[23],"not":[24],"align":[25],"feature":[27,67],"spaces":[28],"closely":[29],"or":[30,109],"are":[31],"expensive":[32],"training":[34,137],"inference.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"present":[41],"X-Norm,":[42],"a":[43,134],"novel,":[44],"simple":[45],"efficient":[47],"method":[48],"bimodal":[50],"that":[52,105],"generates":[53],"exchanges":[55],"limited":[56],"but":[57],"meaningful":[58],"normalization":[59],"parameters":[60],"between":[61],"implicitly":[64],"aligning":[65],"spaces.":[68],"We":[69],"conduct":[70],"extensive":[71],"experiments":[72],"on":[73],"two":[74],"tasks":[75],"of":[76],"emotion":[77,94],"action":[79,99],"recognition":[80,95],"with":[81,133],"architectures":[83],"including":[84,117],"Transformer-based":[85],"CNN-based":[87],"models":[88],"using":[89],"IEMOCAP":[90],"MSP-IMPROV":[92],"EPIC-KITCHENS":[97],"recognition.":[100],"The":[101],"experimental":[102],"results":[103],"show":[104],"X-Norm":[106],"achieves":[107],"comparable":[108],"superior":[110],"performance":[111],"compared":[112],"existing":[115],"methods":[116],"early":[118],"late":[120],"fusion,":[121],"Gradient-Blending":[122],"(G-Blend)":[123],"[44],":[124],"Tensor":[125],"Fusion":[126],"Network,":[127],"[48]":[128],"Transformer":[131],"[40],":[132],"relatively":[135],"low":[136],"cost.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
