{"id":"https://openalex.org/W7138221405","doi":"https://doi.org/10.48550/arxiv.2603.14361","title":"BROTHER: Behavioral Recognition Optimized Through Heterogeneous Ensemble Regularization for Ambivalence and Hesitancy","display_name":"BROTHER: Behavioral Recognition Optimized Through Heterogeneous Ensemble Regularization for Ambivalence and Hesitancy","publication_year":2026,"publication_date":"2026-03-15","ids":{"openalex":"https://openalex.org/W7138221405","doi":"https://doi.org/10.48550/arxiv.2603.14361"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14361","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14361","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.14361","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129744182","display_name":"Alexandre Pereira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pereira, Alexandre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129735282","display_name":"Bruno Fernandes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fernandes, Bruno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129704992","display_name":"Pablo Barros","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barros, Pablo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.0010000000474974513,"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/T11448","display_name":"Face recognition and analysis","score":0.000699999975040555,"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/overfitting","display_name":"Overfitting","score":0.6732000112533569},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4945000112056732},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4410000145435333},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.35670000314712524},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.35499998927116394},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.35359999537467957},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.35179999470710754},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.35010001063346863}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7146000266075134},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6732000112533569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6516000032424927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5950999855995178},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.35359999537467957},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C153668964","wikidata":"https://www.wikidata.org/wiki/Q27636","display_name":"Majority rule","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2669999897480011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14361","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14361","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.14361","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14361","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recognizing":[0],"complex":[1],"behavioral":[2,81,223],"states":[3],"such":[4],"as":[5,27,168,207],"Ambivalence":[6],"and":[7,35,64,80,105,205],"Hesitancy":[8],"(A/H)":[9],"in":[10,18],"naturalistic":[11],"video":[12,54],"settings":[13],"remains":[14],"a":[15,43,68,96,134,147,188,208,218],"significant":[16],"challenge":[17],"affective":[19],"computing.":[20],"Unlike":[21],"basic":[22],"facial":[23],"expressions,":[24],"A/H":[25,51],"manifests":[26],"subtle,":[28],"multimodal":[29,46,185,209],"conflicts":[30],"that":[31,163,202],"require":[32],"deep":[33],"contextual":[34],"temporal":[36,77],"understanding.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,89,132],"propose":[42],"highly":[44],"regularized,":[45],"fusion":[47],"pipeline":[48],"to":[49,75,120,128,152],"predict":[50],"at":[52],"the":[53,85,108,129,169,195],"level.":[55],"We":[56],"extract":[57],"robust":[58,219],"unimodal":[59],"features":[60,166],"from":[61],"visual,":[62],"acoustic,":[63],"linguistic":[65,165],"data,":[66],"introducing":[67],"specialized":[69],"statistical":[70],"text":[71],"modality":[72,93],"explicitly":[73],"designed":[74],"capture":[76],"speech":[78],"variations":[79],"cues.":[82],"To":[83],"identify":[84],"most":[86,109],"effective":[87],"representations,":[88],"evaluate":[90],"15":[91],"distinct":[92],"combinations":[94],"across":[95],"committee":[97],"of":[98,173,192],"machine":[99],"learning":[100],"classifiers":[101],"(MLP,":[102],"Random":[103],"Forest,":[104],"GBDT),":[106],"selecting":[107],"well-calibrated":[110],"models":[111,125],"based":[112],"on":[113,194],"validation":[114],"Binary":[115],"Cross-Entropy":[116],"(BCE)":[117],"loss.":[118],"Furthermore,":[119],"optimally":[121],"fuse":[122],"these":[123],"heterogeneous":[124],"without":[126],"overfitting":[127],"training":[130],"distribution,":[131],"implement":[133],"Particle":[135],"Swarm":[136],"Optimization":[137],"(PSO)":[138],"hard-voting":[139],"ensemble.":[140],"The":[141],"PSO":[142,178],"fitness":[143],"function":[144],"dynamically":[145],"incorporates":[146],"train-validation":[148],"gap":[149],"penalty":[150],"(lambda)":[151],"actively":[153],"suppress":[154],"redundant":[155],"or":[156],"overfitted":[157],"classifiers.":[158],"Our":[159],"comprehensive":[160],"evaluation":[161],"demonstrates":[162],"while":[164],"serve":[167],"strongest":[170],"independent":[171],"predictor":[172],"A/H,":[174],"our":[175],"heavily":[176],"regularized":[177],"ensemble":[179],"(lambda":[180],"=":[181],"0.2)":[182],"effectively":[183],"harnesses":[184],"synergies,":[186],"achieving":[187],"peak":[189],"Macro":[190],"F1-score":[191],"0.7465":[193],"unseen":[196],"test":[197],"set.":[198],"These":[199],"results":[200],"emphasize":[201],"treating":[203],"ambivalence":[204],"hesitancy":[206],"conflict,":[210],"evaluated":[211],"through":[212],"an":[213],"intelligently":[214],"weighted":[215],"committee,":[216],"provides":[217],"framework":[220],"for":[221],"in-the-wild":[222],"analysis.":[224]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-18T00:00:00"}