{"id":"https://openalex.org/W4403913342","doi":"https://doi.org/10.1145/3678957.3685704","title":"Towards Automated Annotation of Infant-Caregiver Engagement Phases with Multimodal Foundation Models","display_name":"Towards Automated Annotation of Infant-Caregiver Engagement Phases with Multimodal Foundation Models","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403913342","doi":"https://doi.org/10.1145/3678957.3685704"},"language":"en","primary_location":{"id":"doi:10.1145/3678957.3685704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678957.3685704","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Multimodel Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3678957.3685704","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072317323","display_name":"Daksitha Senel Withanage Don","orcid":"https://orcid.org/0009-0003-8831-9795"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Daksitha Senel Withanage Don","raw_affiliation_strings":["Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany"],"raw_orcid":"https://orcid.org/0009-0003-8831-9795","affiliations":[{"raw_affiliation_string":"Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060629499","display_name":"Dominik Schiller","orcid":"https://orcid.org/0000-0001-7364-5772"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Schiller","raw_affiliation_strings":["Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7364-5772","affiliations":[{"raw_affiliation_string":"Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017509089","display_name":"Tobias Hallmen","orcid":"https://orcid.org/0009-0005-6450-5694"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Hallmen","raw_affiliation_strings":["Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany"],"raw_orcid":"https://orcid.org/0009-0005-6450-5694","affiliations":[{"raw_affiliation_string":"Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043580137","display_name":"Silvan Mertes","orcid":"https://orcid.org/0000-0001-5230-5218"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Silvan Mertes","raw_affiliation_strings":["Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5230-5218","affiliations":[{"raw_affiliation_string":"Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013717782","display_name":"Tobias Baur","orcid":"https://orcid.org/0000-0002-2797-605X"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Baur","raw_affiliation_strings":["Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2797-605X","affiliations":[{"raw_affiliation_string":"Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023000450","display_name":"Florian Lingenfelser","orcid":"https://orcid.org/0000-0003-1582-9850"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Lingenfelser","raw_affiliation_strings":["Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1582-9850","affiliations":[{"raw_affiliation_string":"Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073766663","display_name":"Mitho M\u00fcller","orcid":"https://orcid.org/0000-0002-8431-540X"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mitho M\u00fcller","raw_affiliation_strings":["Department of Psychology, Ludwig-Maximilians-University Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8431-540X","affiliations":[{"raw_affiliation_string":"Department of Psychology, Ludwig-Maximilians-University Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114465227","display_name":"Lea Kaubisch","orcid":"https://orcid.org/0000-0001-6540-3140"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lea Kaubisch","raw_affiliation_strings":["Department of Psychology, Ludwig-Maximilians-University Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6540-3140","affiliations":[{"raw_affiliation_string":"Department of Psychology, Ludwig-Maximilians-University Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087115470","display_name":"Corinna Reck","orcid":"https://orcid.org/0000-0003-0759-1563"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Prof. Dr. Corinna Reck","raw_affiliation_strings":["Department of Psychology, Ludwig Maximilian University of Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0759-1563","affiliations":[{"raw_affiliation_string":"Department of Psychology, Ludwig Maximilian University of Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056684559","display_name":"Elisabeth Andr\u00e9","orcid":"https://orcid.org/0000-0002-2367-162X"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elisabeth Andr\u00e9","raw_affiliation_strings":["Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2367-162X","affiliations":[{"raw_affiliation_string":"Chair for Human-Centered Artificial Intelligence, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5072317323"],"corresponding_institution_ids":["https://openalex.org/I179225836"],"apc_list":null,"apc_paid":null,"fwci":0.3311,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67238454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"428","last_page":"438"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9969000220298767,"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/T12031","display_name":"Speech and dialogue systems","score":0.9969000220298767,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9876999855041504,"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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9656999707221985,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.735753059387207},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7053436040878296},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5873468518257141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40477970242500305},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34857672452926636},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06782323122024536}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.735753059387207},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7053436040878296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5873468518257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40477970242500305},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34857672452926636},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06782323122024536},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3678957.3685704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678957.3685704","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Multimodel Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:116607","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-1166079","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/116607/116607.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"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":null,"raw_type":"doc-type:conferenceobject"}],"best_oa_location":{"id":"doi:10.1145/3678957.3685704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678957.3685704","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Multimodel Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2249928863","display_name":null,"funder_award_id":"490909448","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1485022657","https://openalex.org/W1978968062","https://openalex.org/W1986811352","https://openalex.org/W1991668076","https://openalex.org/W2015457778","https://openalex.org/W2091341174","https://openalex.org/W2150417125","https://openalex.org/W2166996472","https://openalex.org/W2404829057","https://openalex.org/W2473242311","https://openalex.org/W2511551285","https://openalex.org/W2569702113","https://openalex.org/W2625366777","https://openalex.org/W2769581371","https://openalex.org/W2803693622","https://openalex.org/W2911697343","https://openalex.org/W2949662773","https://openalex.org/W2995603090","https://openalex.org/W2998994232","https://openalex.org/W3038927689","https://openalex.org/W3087489940","https://openalex.org/W3094506883","https://openalex.org/W3104792420","https://openalex.org/W3159481202","https://openalex.org/W4244490634","https://openalex.org/W4247355006","https://openalex.org/W4249450269","https://openalex.org/W6824949632"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328"],"abstract_inverted_index":{"Caregiver":[0,68],"mental":[1],"health":[2],"disorders":[3],"increase":[4],"the":[5,40,65,112,149],"risk":[6],"of":[7,17,98,114,200],"insecure":[8],"infant":[9,164],"attachment":[10],"and":[11,23,31,64,67,90,141,151],"can":[12],"negatively":[13],"impact":[14],"multiple":[15],"aspects":[16],"child":[18],"development,":[19],"including":[20],"cognitive,":[21],"emotional,":[22],"social":[24],"growth.":[25],"Infant-caregiver":[26],"interactions":[27,116],"contain":[28],"subtle":[29],"psychological":[30,58],"behavioral":[32],"cues":[33],"that":[34,110,135],"reveal":[35],"these":[36,62],"adverse":[37],"effects,":[38],"underscoring":[39],"need":[41],"for":[42,60,81],"analytical":[43],"methods":[44,202],"to":[45],"assess":[46],"them":[47],"effectively.":[48],"The":[49],"Face-to-Face-Still-Face":[50],"(FFSF)":[51],"paradigm":[52],"is":[53,88],"a":[54,78,95,107],"key":[55],"approach":[56,125],"in":[57,161,203],"research":[59],"investigating":[61],"dynamics,":[63],"Infant":[66],"Engagement":[69],"Phases":[70],"revised":[71],"German":[72],"edition":[73],"(ICEP-R)":[74],"annotation":[75,87,113],"scheme":[76],"provides":[77],"structured":[79],"framework":[80],"evaluating":[82],"FFSF":[83,130],"interactions.":[84],"However,":[85],"manual":[86],"labor-intensive":[89],"limits":[91],"scalability,":[92],"thus":[93],"hindering":[94],"deeper":[96],"understanding":[97],"early":[99],"developmental":[100],"impairments.":[101],"To":[102,183],"address":[103],"this,":[104],"we":[105,187],"developed":[106],"computational":[108,201],"method":[109],"automates":[111],"caregiver-infant":[115],"using":[117],"features":[118],"extracted":[119],"from":[120],"audio-visual":[121],"foundational":[122],"models.":[123],"Our":[124],"was":[126],"tested":[127],"on":[128,138,148],"92":[129],"video":[131],"sessions.":[132],"Findings":[133],"demonstrate":[134],"models":[136,157,172],"based":[137],"bidirectional":[139,155],"LSTM":[140,156],"linear":[142,171],"classifiers":[143],"show":[144,173],"varying":[145],"effectiveness":[146],"depending":[147],"role":[150],"feature":[152,179,191],"modality.":[153],"Specifically,":[154],"generally":[158],"perform":[159],"better":[160],"predicting":[162],"complex":[163],"engagement":[165],"phases":[166],"across":[167],"multimodal":[168],"features,":[169],"while":[170],"competitive":[174],"performance,":[175],"particularly":[176],"with":[177,194],"unimodal":[178],"encodings":[180],"like":[181],"Wav2Vec2-BERT.":[182],"support":[184],"further":[185],"research,":[186],"share":[188],"our":[189],"raw":[190],"dataset":[192],"annotated":[193],"ICEP-R":[195],"labels,":[196],"enabling":[197],"broader":[198],"refinement":[199],"this":[204],"area.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2024-10-31T00:00:00"}