{"id":"https://openalex.org/W4403913013","doi":"https://doi.org/10.1145/3678957.3685709","title":"Generalization Boost in Bimodal Classification via Data Fusion Trained on Sparse Datasets","display_name":"Generalization Boost in Bimodal Classification via Data Fusion Trained on Sparse Datasets","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403913013","doi":"https://doi.org/10.1145/3678957.3685709"},"language":"en","primary_location":{"id":"doi:10.1145/3678957.3685709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678957.3685709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Multimodel Interaction","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/A5113818347","display_name":"Wen-Shi Yu","orcid":"https://orcid.org/0000-0002-0760-1437"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wentao Yu","raw_affiliation_strings":["Electronic Systems of Medical Engineering, TU Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0760-1437","affiliations":[{"raw_affiliation_string":"Electronic Systems of Medical Engineering, TU Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007017640","display_name":"Dorothea Kolossa","orcid":"https://orcid.org/0000-0003-0678-3053"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dorothea Kolossa","raw_affiliation_strings":["Electronic Systems of Medical Engineering, TU Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0678-3053","affiliations":[{"raw_affiliation_string":"Electronic Systems of Medical Engineering, TU Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075524022","display_name":"Robert M. Nickel","orcid":"https://orcid.org/0009-0005-5007-5355"},"institutions":[{"id":"https://openalex.org/I131221577","display_name":"Bucknell University","ror":"https://ror.org/00fc1qt65","country_code":"US","type":"education","lineage":["https://openalex.org/I131221577"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Nickel","raw_affiliation_strings":["Electrical and Computer Engineering Bucknell University, United States"],"raw_orcid":"https://orcid.org/0009-0005-5007-5355","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Bucknell University, United States","institution_ids":["https://openalex.org/I131221577"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"173","last_page":"181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9858999848365784,"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":0.9858999848365784,"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":0.9837999939918518,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9419000148773193,"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/generalization","display_name":"Generalization","score":0.7162397503852844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6653028726577759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5906678438186646},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.561747133731842},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5057659149169922},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4982931613922119},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4109892249107361},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1362987756729126}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7162397503852844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6653028726577759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5906678438186646},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.561747133731842},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5057659149169922},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4982931613922119},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4109892249107361},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1362987756729126},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3678957.3685709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678957.3685709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Multimodel Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1985690171","https://openalex.org/W2035777533","https://openalex.org/W2104263160","https://openalex.org/W2133115605","https://openalex.org/W2788241093","https://openalex.org/W3035333188","https://openalex.org/W3115365386","https://openalex.org/W3135367836","https://openalex.org/W3161541317","https://openalex.org/W3161559694","https://openalex.org/W3164472354","https://openalex.org/W4220861777","https://openalex.org/W4287219610","https://openalex.org/W4362619048"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2152662039"],"abstract_inverted_index":{"For":[0],"internet":[1],"users":[2],"it":[3],"is":[4,62,114,118],"frequently":[5,176],"challenging":[6],"to":[7,18,34,67,204,255],"properly":[8],"navigate":[9],"and":[10,65,157,185,237,244],"interpret":[11],"the":[12,28,53,71,75,142,150,158,174,180,196,200,209,218,231,248,252],"overwhelming":[13],"amount":[14,108],"of":[15,48,55,74,109,129,173,199,208,230,251],"information":[16,76,98],"available":[17],"them.":[19],"Multimodal":[20],"artificial":[21],"intelligence":[22],"(AI)":[23],"systems":[24,51],"can":[25],"aid":[26],"in":[27,100,102,131,228],"process;":[29],"for":[30,153,164,240],"example,":[31],"by":[32,38,70,194],"helping":[33],"debunk":[35],"misinformation,":[36],"or":[37],"placing":[39],"video":[40],"content":[41],"into":[42],"a":[43,59,85,105,125,137],"proper":[44],"context.":[45],"The":[46,116,168],"training":[47,112,190,243],"commensurate":[49],"AI":[50],"requires":[52],"labelling":[54],"sizable":[56],"multimodal":[57],"datasets,":[58],"process":[60],"that":[61,217],"very":[63,106],"time-consuming":[64],"prone":[66],"being":[68],"outpaced":[69],"rapid":[72],"changes":[73],"landscape.":[77],"To":[78],"address":[79],"this":[80],"problem,":[81],"we":[82,123],"are":[83],"introducing":[84],"hybrid":[86,220],"fusion":[87,221],"algorithm,":[88],"Bimodal":[89],"Gaussian-Logits":[90],"glObal":[91],"stream":[92],"Weighting":[93],"(BiGLOW),":[94],"which":[95,103],"performs":[96],"effective":[97],"integration":[99],"scenarios":[101],"only":[104],"limited":[107],"bimodally":[110,201],"labelled":[111,202],"data":[113,191,211],"available.":[115],"method":[117,144,254],"motivated":[119],"from":[120],"Bayesian":[121,258],"inference;":[122],"model":[124,232,242],"modality-weighted":[126],"linear":[127],"combination":[128],"differences":[130],"logits":[132],"between":[133],"class":[134],"pairs":[135],"through":[136],"Gaussian":[138],"distribution.":[139],"We":[140,246],"evaluated":[141],"proposed":[143,219,253],"with":[145,188],"two":[146,169],"bimodal":[147],"multiclass":[148],"datasets:":[149],"Fakeddit":[151],"dataset":[152],"fake":[154],"news":[155],"classification":[156],"TAU":[159],"Audio-Visual":[160],"Urban":[161],"Scenes":[162],"2021":[163],"urban":[165],"scene":[166],"identification.":[167],"datasets":[170],"capture":[171],"four":[172],"most":[175],"used":[177],"modalities":[178],"on":[179],"web:":[181],"text,":[182],"images,":[183],"audio,":[184],"video.":[186],"Scenarios":[187],"scarce":[189],"were":[192],"created":[193],"reducing":[195],"respective":[197],"size":[198],"set":[203],"various":[205],"small":[206],"fractions":[207],"overall":[210],"size.":[212],"Our":[213],"experimental":[214],"results":[215],"indicate":[216],"algorithm":[222],"surpasses":[223],"competing":[224],"purely":[225],"neural-network-based":[226],"models":[227],"terms":[229],"complexity,":[233],"average":[234],"accuracy,":[235],"robustness,":[236],"time":[238],"requirements":[239],"both":[241],"evaluation.":[245],"attribute":[247],"improved":[249],"performance":[250],"its":[256],"implied,":[257],"inference":[259],"inspired":[260],"regularization.":[261]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}