{"id":"https://openalex.org/W4403780549","doi":"https://doi.org/10.1145/3664647.3688988","title":"DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation","display_name":"DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780549","doi":"https://doi.org/10.1145/3664647.3688988"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3688988","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5019391894","display_name":"Jia Li","orcid":"https://orcid.org/0000-0001-9446-249X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9446-249X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058525575","display_name":"Yangchen Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangchen Yu","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-7261-1677","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101289433","display_name":"Yin Chen","orcid":"https://orcid.org/0009-0002-4436-6613"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Chen","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-4436-6613","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092339698","display_name":"Yu Zhang","orcid":"https://orcid.org/0009-0003-3350-7609"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-3350-7609","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082934998","display_name":"Peng Jia","orcid":"https://orcid.org/0009-0001-5878-0922"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jia","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0001-5878-0922","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103497390","display_name":"Yunbo Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Xu","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-0519-147X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112669498","display_name":"Ziqiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqiang Li","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-9717-7416","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-7735","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5461-3986","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11397","last_page":"11403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.998199999332428,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9966999888420105,"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":0.9739000201225281,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6410311460494995},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6340309381484985},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6288827657699585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5824891924858093},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.43117645382881165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4293835759162903},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37009045481681824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32265228033065796},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15117233991622925},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11485129594802856},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09947335720062256},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07537314295768738}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6410311460494995},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6340309381484985},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6288827657699585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5824891924858093},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.43117645382881165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4293835759162903},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37009045481681824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32265228033065796},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15117233991622925},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11485129594802856},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09947335720062256},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07537314295768738},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3688988","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2042587338","https://openalex.org/W2085662862","https://openalex.org/W2105410877","https://openalex.org/W2559085405","https://openalex.org/W2755291975","https://openalex.org/W2782668511","https://openalex.org/W2964010806","https://openalex.org/W2995682556","https://openalex.org/W3101726544","https://openalex.org/W3183885459","https://openalex.org/W3184185352","https://openalex.org/W3205504809","https://openalex.org/W4226033575","https://openalex.org/W4226276149","https://openalex.org/W4282936521","https://openalex.org/W4288099396","https://openalex.org/W4387969083","https://openalex.org/W4388192187","https://openalex.org/W4402712443","https://openalex.org/W4402916290"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2152662039"],"abstract_inverted_index":{"Engagement":[0,121],"estimation":[1],"plays":[2],"a":[3,29,57,142],"crucial":[4],"role":[5],"in":[6,15,51,118,130],"understanding":[7],"human":[8,49],"social":[9],"behaviors,":[10],"attracting":[11],"increasing":[12],"research":[13],"interests":[14],"fields":[16],"such":[17],"as":[18],"affective":[19],"computing":[20],"and":[21,44,65,87,107,153,164],"human-computer":[22],"interaction.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"propose":[28],"Dialogue-Aware":[30,100],"Transformer":[31,101],"framework":[32],"(DAT)":[33],"with":[34],"Modality-Group":[35],"Fusion":[36],"(MGF),":[37],"which":[38],"relies":[39],"solely":[40],"on":[41,147],"audio-visual":[42,78],"input":[43],"is":[45],"language-independent,":[46],"for":[47,71],"estimating":[48],"engagement":[50,96],"conversations.":[52],"Specifically,":[53],"our":[54,139],"method":[55,114],"employs":[56],"modality-group":[58],"fusion":[59],"strategy":[60,81],"that":[61],"independently":[62],"fuses":[63],"audio":[64],"visual":[66],"features":[67],"within":[68],"each":[69,72],"modality":[70],"person":[73],"before":[74],"inferring":[75],"the":[76,84,93,98,104,119,135,148,160],"entire":[77],"content.":[79],"This":[80],"significantly":[82],"enhances":[83],"model's":[85],"performance":[86],"robustness.":[88],"Additionally,":[89],"to":[90],"better":[91],"estimate":[92],"target":[94],"participant's":[95,105],"levels,":[97],"introduced":[99],"considers":[102],"both":[103],"behavior":[106],"cues":[108],"from":[109],"their":[110],"conversational":[111],"partners.":[112],"Our":[113],"was":[115],"rigorously":[116],"tested":[117],"Multi-Domain":[120],"Estimation":[122],"Challenge":[123],"held":[124],"by":[125],"MultiMediate'24,":[126],"demonstrating":[127],"notable":[128],"improvements":[129],"engagement-level":[131],"regression":[132],"precision":[133],"over":[134],"baseline":[136],"model.":[137],"Notably,":[138],"approach":[140],"achieves":[141],"CCC":[143,156],"score":[144],"of":[145,157],"0.76":[146],"NoXi":[149,161],"Base":[150],"test":[151,166],"set":[152],"an":[154],"average":[155],"0.64":[158],"across":[159],"Base,":[162],"NoXi-Add,":[163],"MPIIGI":[165],"sets.":[167],"The":[168],"source":[169],"code":[170],"will":[171],"be":[172],"available":[173],"at":[174],"https://github.com/MSA-LMC/DAT.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
