{"id":"https://openalex.org/W4403713302","doi":"https://doi.org/10.1145/3689092.3689409","title":"Are You Paying Attention? Multimodal Linear Attention Transformers for Affect Prediction in Video Conversations","display_name":"Are You Paying Attention? Multimodal Linear Attention Transformers for Affect Prediction in Video Conversations","publication_year":2024,"publication_date":"2024-10-23","ids":{"openalex":"https://openalex.org/W4403713302","doi":"https://doi.org/10.1145/3689092.3689409"},"language":"en","primary_location":{"id":"doi:10.1145/3689092.3689409","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689092.3689409","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3689092.3689409?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3689092.3689409?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114389142","display_name":"Jia Qing Poh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085930","display_name":"Heriot-Watt University Malaysia","ror":"https://ror.org/0059w0420","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210085930"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Jia Qing Poh","raw_affiliation_strings":["School of Mathematical and Computer Sciences, Heriot-Watt University Malaysia, Putrajaya, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Mathematical and Computer Sciences, Heriot-Watt University Malaysia, Putrajaya, Malaysia","institution_ids":["https://openalex.org/I4210085930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076753547","display_name":"John See","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085930","display_name":"Heriot-Watt University Malaysia","ror":"https://ror.org/0059w0420","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210085930"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"John See","raw_affiliation_strings":["School of Mathematical and Computer Sciences, Heriot-Watt University Malaysia, Putrajaya, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Mathematical and Computer Sciences, Heriot-Watt University Malaysia, Putrajaya, Malaysia","institution_ids":["https://openalex.org/I4210085930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072025713","display_name":"Neamat El Gayar","orcid":"https://orcid.org/0000-0003-1467-1115"},"institutions":[{"id":"https://openalex.org/I4210149788","display_name":"Heriot-Watt University Dubai","ror":"https://ror.org/058tx1a56","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210149788"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Neamat El Gayar","raw_affiliation_strings":["School of Mathematical and Computer Sciences, Heriot-Watt University Dubai, Dubai, United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"School of Mathematical and Computer Sciences, Heriot-Watt University Dubai, Dubai, United Arab Emirates","institution_ids":["https://openalex.org/I4210149788"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046326626","display_name":"Lai-Kuan Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Lai-Kuan Wong","raw_affiliation_strings":["Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114389142"],"corresponding_institution_ids":["https://openalex.org/I4210085930"],"apc_list":null,"apc_paid":null,"fwci":0.5269,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71568651,"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":"15","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9944000244140625,"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":0.9944000244140625,"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/T12031","display_name":"Speech and dialogue systems","score":0.9585000276565552,"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/T14394","display_name":"Cognitive Science and Education Research","score":0.9585000276565552,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.6899436712265015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5881607532501221},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5004539489746094},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24803030490875244},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12943881750106812},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07426267862319946},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.0701352059841156}],"concepts":[{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.6899436712265015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5881607532501221},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5004539489746094},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24803030490875244},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12943881750106812},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07426267862319946},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0701352059841156},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3689092.3689409","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689092.3689409","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3689092.3689409?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:shdl.mmu.edu.my:13271","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196753","display_name":"Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173029219","host_organization_name":"Multimedia University","host_organization_lineage":["https://openalex.org/I173029219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"}],"best_oa_location":{"id":"doi:10.1145/3689092.3689409","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689092.3689409","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3689092.3689409?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403713302.pdf","grobid_xml":"https://content.openalex.org/works/W4403713302.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2002591263","https://openalex.org/W2083021723","https://openalex.org/W2135394513","https://openalex.org/W2612690371","https://openalex.org/W2962960500","https://openalex.org/W2964346351","https://openalex.org/W2981851019","https://openalex.org/W3001587372","https://openalex.org/W3021080764","https://openalex.org/W3049446265","https://openalex.org/W3093370878","https://openalex.org/W3094550259","https://openalex.org/W3103291722","https://openalex.org/W3120680448","https://openalex.org/W3173365702","https://openalex.org/W3205743929","https://openalex.org/W4200633770","https://openalex.org/W4214612132","https://openalex.org/W4283397308","https://openalex.org/W4376226279","https://openalex.org/W4379382378","https://openalex.org/W4382240624","https://openalex.org/W4387698227"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2560936962","https://openalex.org/W2788727012","https://openalex.org/W4388203630","https://openalex.org/W2390279801","https://openalex.org/W2526386912","https://openalex.org/W4391913857","https://openalex.org/W2358668433"],"abstract_inverted_index":{"The":[0],"post-COVID-19":[1],"era":[2],"has":[3],"seen":[4],"continual":[5],"adoption":[6],"and":[7,45,109,124],"reliance":[8],"on":[9],"video-based":[10,116],"communication,":[11],"underscoring":[12],"the":[13,60,66,74,129],"need":[14],"for":[15,115,120],"unobtrusive":[16],"affect":[17],"recognition":[18,31,113],"in":[19,32,72,128],"digital":[20,126],"interactions.":[21],"This":[22,102],"paper":[23],"proposes":[24],"an":[25],"efficient":[26,110],"multimodal":[27,111],"approach":[28,68],"to":[29,41,105],"emotion":[30,112],"video":[33],"conversational":[34],"scenarios,":[35],"leveraging":[36],"linear":[37,51],"attention-based":[38],"Transformer":[39],"networks":[40],"process":[42],"both":[43],"visual":[44],"audio":[46],"cues.":[47],"We":[48],"explore":[49],"various":[50],"attention":[52],"mechanisms,":[53],"comparing":[54],"them":[55],"with":[56,118],"classical":[57],"self-attention.":[58],"Using":[59],"K-EmoCon":[61],"dataset,":[62],"we":[63],"demonstrate":[64],"that":[65,89],"proposed":[67],"yields":[69],"competitive":[70],"performance":[71],"predicting":[73],"affective":[75],"states":[76],"of":[77],"conversing":[78],"persons":[79],"while":[80],"significantly":[81],"improving":[82],"memory":[83],"efficiency.":[84],"Our":[85],"ablation":[86],"studies":[87],"reveal":[88],"carefully":[90],"tuned":[91],"simple":[92],"fusion":[93],"methods":[94],"can":[95],"match":[96],"or":[97],"exceed":[98],"more":[99,107],"complex":[100],"approaches.":[101],"research":[103],"contributes":[104],"developing":[106],"accessible":[108],"systems":[114],"conversations,":[117],"applications":[119],"enhancing":[121],"remote":[122],"communication":[123],"monitoring":[125],"well-being":[127],"post-pandemic":[130],"era.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-12T06:13:28.667946","created_date":"2025-10-10T00:00:00"}
