{"id":"https://openalex.org/W4402980239","doi":"https://doi.org/10.1109/icme57554.2024.10687371","title":"Cross-Attention is not always needed: Dynamic Cross-Attention for Audio-Visual Dimensional Emotion Recognition","display_name":"Cross-Attention is not always needed: Dynamic Cross-Attention for Audio-Visual Dimensional Emotion Recognition","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980239","doi":"https://doi.org/10.1109/icme57554.2024.10687371"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687371","doi":"https://doi.org/10.1109/icme57554.2024.10687371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687371","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.19554","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021177750","display_name":"R. Gnana Praveen","orcid":"https://orcid.org/0000-0002-4698-9198","observed_orcids":["https://orcid.org/0000-0002-4698-9198"]},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"R. Gnana Praveen","raw_affiliation_strings":["Computer Research Institute of Montreal (CRIM),Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal (CRIM),Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055570520","display_name":"Jahangir Alam","orcid":"https://orcid.org/0000-0003-1081-3665","observed_orcids":["https://orcid.org/0000-0003-1081-3665"]},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jahangir Alam","raw_affiliation_strings":["Computer Research Institute of Montreal (CRIM),Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal (CRIM),Canada","institution_ids":["https://openalex.org/I4210111842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210111842"],"apc_list":null,"apc_paid":null,"fwci":0.9161,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77641385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0,"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/audio-visual-emotion-recognition","display_name":"audio-visual emotion recognition","score":0.9599999785423279},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.6650000214576721},{"id":"https://openalex.org/keywords/gating-mechanism","display_name":"gating mechanism","score":0.7360000014305115},{"id":"https://openalex.org/keywords/video-based-emotion-recognition","display_name":"video-based emotion recognition","score":0.8500000238418579},{"id":"https://openalex.org/keywords/aff-wild2","display_name":"Aff-Wild2","score":0.9929999709129333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6743443608283997},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6704584360122681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5711135864257812},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.543419599533081},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4854348301887512},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4062216579914093},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.36158931255340576},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17483225464820862},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.13872307538986206},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icme57554.2024.10687371","doi":"https://doi.org/10.1109/icme57554.2024.10687371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687371","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.19554","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.19554","pdf_url":"https://arxiv.org/pdf/2403.19554","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.19554","doi":"https://doi.org/10.48550/arxiv.2403.19554","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.19554","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.19554","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.19554","pdf_url":"https://arxiv.org/pdf/2403.19554","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402980239.pdf","grobid_xml":"https://content.openalex.org/works/W4402980239.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2045528981","https://openalex.org/W2610961739","https://openalex.org/W2955022262","https://openalex.org/W2963334011","https://openalex.org/W2998562534","https://openalex.org/W3006361992","https://openalex.org/W3095251683","https://openalex.org/W3096963953","https://openalex.org/W3109188747","https://openalex.org/W3137028092","https://openalex.org/W3204047821","https://openalex.org/W3209279902","https://openalex.org/W3211666705","https://openalex.org/W4205462621","https://openalex.org/W4213188130","https://openalex.org/W4214814722","https://openalex.org/W4292794079","https://openalex.org/W4292829055","https://openalex.org/W4313591463","https://openalex.org/W4372259790","https://openalex.org/W4376226279","https://openalex.org/W4385801060","https://openalex.org/W4385805114","https://openalex.org/W4385815442"],"related_works":["https://openalex.org/W4398230549","https://openalex.org/W4400276083","https://openalex.org/W4313591463","https://openalex.org/W3211666705","https://openalex.org/W4221139382","https://openalex.org/W4390905815","https://openalex.org/W4400527613","https://openalex.org/W4414197664","https://openalex.org/W4285047006","https://openalex.org/W6977134051"],"abstract_inverted_index":{"In":[0],"video-based":[1],"emotion":[2],"recognition,":[3],"audio":[4],"and":[5,90,117,131],"visual":[6],"modalities":[7],"are":[8],"often":[9],"expected":[10],"to":[11,82],"have":[12],"a":[13,74,98],"complementary":[14,28,70,100],"relationship,":[15,101],"which":[16],"is":[17,80],"widely":[18],"explored":[19],"using":[20],"cross-attention.":[21],"However,":[22],"they":[23,96],"may":[24],"also":[25,121],"exhibit":[26,97],"weak":[27,69],"relationships,":[29],"resulting":[30],"in":[31],"poor":[32],"representations":[33],"of":[34,41,86,109,129],"audio-visual":[35],"features,":[36],"thus":[37],"degrading":[38],"the":[39,42,62,84,87,107,110,114,123,134,139],"performance":[40,108,140],"system.":[43],"To":[44],"address":[45],"this":[46],"issue,":[47],"we":[48],"propose":[49],"Dynamic":[50],"Cross-Attention":[51],"(DCA)":[52],"that":[53,133],"can":[54],"dynamically":[55],"select":[56],"cross-attended":[57,92],"or":[58,68],"unattended":[59,103],"features":[60,93],"on":[61,65,113,141],"fly":[63],"based":[64],"their":[66],"strong":[67,99],"relationships":[71],"respectively.":[72],"Specifically,":[73],"simple":[75],"yet":[76],"efficient":[77],"gating":[78],"layer":[79],"designed":[81],"evaluate":[83,106],"contribution":[85],"cross-attention":[88,130],"mechanism":[89],"choose":[91],"only":[94],"when":[95],"otherwise":[102],"features.":[104],"We":[105,120],"proposed":[111,124,135],"approach":[112,125],"challenging":[115],"RECOLA":[116],"Aff-Wild2":[118],"datasets.":[119,143],"compare":[122],"with":[126],"other":[127],"variants":[128],"show":[132],"model":[136],"consistently":[137],"improves":[138],"both":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-10-01T00:00:00"}