{"id":"https://openalex.org/W4411735058","doi":"https://doi.org/10.3389/frai.2025.1516295","title":"Data stream-pairwise bottleneck transformer for engagement estimation from video conversation","display_name":"Data stream-pairwise bottleneck transformer for engagement estimation from video conversation","publication_year":2025,"publication_date":"2025-06-27","ids":{"openalex":"https://openalex.org/W4411735058","doi":"https://doi.org/10.3389/frai.2025.1516295","pmid":"https://pubmed.ncbi.nlm.nih.gov/40656162"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2025.1516295","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1516295","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1516295/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1516295/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103222069","display_name":"Keita Suzuki","orcid":"https://orcid.org/0009-0006-7963-3952"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Keita Suzuki","raw_affiliation_strings":["NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079710814","display_name":"Nobukatsu Hojo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobukatsu Hojo","raw_affiliation_strings":["NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078963513","display_name":"Kazutoshi Shinoda","orcid":"https://orcid.org/0000-0003-1941-6172"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazutoshi Shinoda","raw_affiliation_strings":["NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109312183","display_name":"Saki Mizuno","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Saki Mizuno","raw_affiliation_strings":["NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Informatics Laboratories, NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103222069"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":2125,"currency":"USD","value_usd":2125},"fwci":1.1364,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78459843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"8","issue":null,"first_page":"1516295","last_page":"1516295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.996399998664856,"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":0.996399998664856,"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/T12214","display_name":"Media Influence and Health","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9829000234603882,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7786489725112915},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6419937610626221},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4938128888607025},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.49157819151878357},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4751948118209839},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.45099732279777527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.449668288230896},{"id":"https://openalex.org/keywords/subnetwork","display_name":"Subnetwork","score":0.4399759769439697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42764508724212646},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.427153080701828},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33491313457489014},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09699440002441406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7786489725112915},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6419937610626221},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4938128888607025},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.49157819151878357},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4751948118209839},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.45099732279777527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.449668288230896},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.4399759769439697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42764508724212646},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.427153080701828},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33491313457489014},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09699440002441406},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/frai.2025.1516295","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1516295","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1516295/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:40656162","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40656162","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:doaj.org/article:1377c991a02244d3a37d0efd1d2e3bbd","is_oa":true,"landing_page_url":"https://doaj.org/article/1377c991a02244d3a37d0efd1d2e3bbd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 8 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12246976","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12246976","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Artif Intell","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/frai.2025.1516295","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1516295","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1516295/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411735058.pdf","grobid_xml":"https://content.openalex.org/works/W4411735058.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W2042587338","https://openalex.org/W2045528981","https://openalex.org/W2076434093","https://openalex.org/W2105410877","https://openalex.org/W2158820915","https://openalex.org/W2169570446","https://openalex.org/W2194775991","https://openalex.org/W2286110194","https://openalex.org/W2395639500","https://openalex.org/W2755291975","https://openalex.org/W2888683367","https://openalex.org/W2948683146","https://openalex.org/W2963351448","https://openalex.org/W2963566548","https://openalex.org/W2968917279","https://openalex.org/W2970124028","https://openalex.org/W2980399003","https://openalex.org/W2980495289","https://openalex.org/W2980987964","https://openalex.org/W2981234363","https://openalex.org/W2990138404","https://openalex.org/W3015447373","https://openalex.org/W3089943744","https://openalex.org/W3109970849","https://openalex.org/W3174906557","https://openalex.org/W3187957371","https://openalex.org/W3198429080","https://openalex.org/W4240320754","https://openalex.org/W4285197053","https://openalex.org/W4285250231","https://openalex.org/W4293584584","https://openalex.org/W4299534971","https://openalex.org/W4376455521","https://openalex.org/W4385245566","https://openalex.org/W4385764243","https://openalex.org/W4386981254","https://openalex.org/W4387421711","https://openalex.org/W4387423980","https://openalex.org/W4390421839","https://openalex.org/W4390738632","https://openalex.org/W4402111401","https://openalex.org/W4403780494","https://openalex.org/W6729597402","https://openalex.org/W6739901393","https://openalex.org/W6750227808","https://openalex.org/W6763310536","https://openalex.org/W6767164110","https://openalex.org/W6784203297","https://openalex.org/W6797613833"],"related_works":["https://openalex.org/W2060724872","https://openalex.org/W2082094785","https://openalex.org/W2202198356","https://openalex.org/W3087203342","https://openalex.org/W2377184161","https://openalex.org/W228984114","https://openalex.org/W4226360758","https://openalex.org/W2151093953","https://openalex.org/W2090026684","https://openalex.org/W2907567977"],"abstract_inverted_index":{"This":[0],"study":[1,57],"aims":[2],"to":[3,73,86,159,166,174],"assess":[4],"participant":[5,48,60],"engagement":[6],"in":[7,100],"multiparty":[8],"conversations":[9],"using":[10,130],"video":[11,26,40],"and":[12,27,41,138,168],"audio":[13,28,42],"data.":[14],"For":[15],"this":[16,92],"task,":[17],"the":[18,37,84,96,143,148],"interaction":[19],"among":[20,126],"numerous":[21],"data":[22,128],"streams,":[23],"such":[24,53],"as":[25],"from":[29,157,164,172],"multiple":[30],"participants,":[31],"should":[32],"be":[33],"modeled":[34],"effectively,":[35],"considering":[36],"redundancy":[38,99],"of":[39,80,98],"across":[43,70,113],"frames.":[44],"To":[45,116],"efficiently":[46],"model":[47,85,123,150],"interactions":[49,125],"while":[50],"accounting":[51],"for":[52,124],"redundancy,":[54],"a":[55,77,121],"previous":[56,152],"proposed":[58,149],"inputting":[59],"feature":[61,71],"sequences":[62,72],"into":[63],"global":[64,131],"token-based":[65,132],"transformers,":[66,107,133],"which":[67,108],"constrain":[68],"attention":[69],"pass":[74],"through":[75],"only":[76],"small":[78],"set":[79],"internal":[81],"units,":[82],"allowing":[83],"focus":[87],"on":[88,104,142],"key":[89],"information.":[90],"However,":[91],"approach":[93],"still":[94],"faces":[95],"challenge":[97],"participant-feature":[101],"estimation":[102],"based":[103],"standard":[105],"cross-attention":[106],"can":[109],"connect":[110],"all":[111,127],"frames":[112],"different":[114],"modalities.":[115],"address":[117],"this,":[118],"we":[119],"propose":[120],"joint":[122],"streams":[129],"without":[134],"distinguishing":[135],"between":[136],"cross-modal":[137],"cross-participant":[139],"interactions.":[140],"Experiments":[141],"RoomReader":[144],"corpus":[145],"confirm":[146],"that":[147],"outperforms":[151],"models,":[153],"achieving":[154],"accuracy":[155],"ranging":[156],"0.720":[158],"0.763,":[160],"weighted":[161],"F1":[162,170],"scores":[163,171],"0.733":[165],"0.771,":[167],"macro":[169],"0.236":[173],"0.277.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}