{"id":"https://openalex.org/W4387421131","doi":"https://doi.org/10.1145/3577190.3614114","title":"Component attention network for multimodal dance improvisation recognition","display_name":"Component attention network for multimodal dance improvisation recognition","publication_year":2023,"publication_date":"2023-10-07","ids":{"openalex":"https://openalex.org/W4387421131","doi":"https://doi.org/10.1145/3577190.3614114"},"language":"en","primary_location":{"id":"doi:10.1145/3577190.3614114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3614114","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.05938","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101841222","display_name":"Jia Fu","orcid":"https://orcid.org/0009-0004-3798-8603"},"institutions":[{"id":"https://openalex.org/I2800664555","display_name":"RISE Research Institutes of Sweden","ror":"https://ror.org/03nnxqz81","country_code":"SE","type":"other","lineage":["https://openalex.org/I2800664555"]},{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jia Fu","raw_affiliation_strings":["RISE Research Institutes of Sweden, Sweden and KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0009-0004-3798-8603","affiliations":[{"raw_affiliation_string":"RISE Research Institutes of Sweden, Sweden and KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I2800664555","https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060211170","display_name":"Jiarui Tan","orcid":"https://orcid.org/0009-0004-0768-5505"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jiarui Tan","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0009-0004-0768-5505","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031776591","display_name":"Wenjie Yin","orcid":"https://orcid.org/0000-0002-7189-1336"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Wenjie Yin","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-7189-1336","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065509988","display_name":"Sepideh Pashami","orcid":"https://orcid.org/0000-0003-3272-4145"},"institutions":[{"id":"https://openalex.org/I2800664555","display_name":"RISE Research Institutes of Sweden","ror":"https://ror.org/03nnxqz81","country_code":"SE","type":"other","lineage":["https://openalex.org/I2800664555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sepideh Pashami","raw_affiliation_strings":["RISE Research Institutes of Sweden, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-3272-4145","affiliations":[{"raw_affiliation_string":"RISE Research Institutes of Sweden, Sweden","institution_ids":["https://openalex.org/I2800664555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082269387","display_name":"M\u00e5rten Bj\u00f6rkman","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"M\u00e5rten Bj\u00f6rkman","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-0579-3372","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1754,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.40520134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"114","last_page":"118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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/T12290","display_name":"Human Motion and Animation","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9948999881744385,"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/dance","display_name":"Dance","score":0.743996262550354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6930937170982361},{"id":"https://openalex.org/keywords/improvisation","display_name":"Improvisation","score":0.6824495196342468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5931792259216309},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5692905783653259},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.49154171347618103},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48417928814888},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46116939187049866},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4456746578216553},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33504718542099},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32233452796936035},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07433086633682251}],"concepts":[{"id":"https://openalex.org/C147446459","wikidata":"https://www.wikidata.org/wiki/Q11639","display_name":"Dance","level":2,"score":0.743996262550354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930937170982361},{"id":"https://openalex.org/C125468537","wikidata":"https://www.wikidata.org/wiki/Q214961","display_name":"Improvisation","level":2,"score":0.6824495196342468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5931792259216309},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5692905783653259},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.49154171347618103},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48417928814888},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46116939187049866},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4456746578216553},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33504718542099},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32233452796936035},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07433086633682251},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3577190.3614114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3614114","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2310.05938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.05938","pdf_url":"https://arxiv.org/pdf/2310.05938","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.05938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.05938","pdf_url":"https://arxiv.org/pdf/2310.05938","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387421131.pdf","grobid_xml":"https://content.openalex.org/works/W4387421131.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W2037441721","https://openalex.org/W2058616948","https://openalex.org/W2098562545","https://openalex.org/W2143350951","https://openalex.org/W2157331557","https://openalex.org/W2164186291","https://openalex.org/W2590448177","https://openalex.org/W2594167370","https://openalex.org/W2894880532","https://openalex.org/W2897337310","https://openalex.org/W2903090875","https://openalex.org/W2953267996","https://openalex.org/W2962954622","https://openalex.org/W2963781481","https://openalex.org/W2964015378","https://openalex.org/W2971872524","https://openalex.org/W2995556886","https://openalex.org/W3011028193","https://openalex.org/W3011941208","https://openalex.org/W3012760824","https://openalex.org/W3089943744","https://openalex.org/W3130743176","https://openalex.org/W3184030141","https://openalex.org/W4214925116","https://openalex.org/W4285109943","https://openalex.org/W4285555510"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Dance":[0],"improvisation":[1,149],"is":[2,31],"an":[3,75],"active":[4],"research":[5],"topic":[6],"in":[7,67,122,150],"the":[8,55,68,117,140],"arts.":[9],"Motion":[10],"analysis":[11],"of":[12,39,59,70,119],"improvised":[13],"dance":[14,24,71],"can":[15,45],"be":[16,46],"challenging":[17],"due":[18],"to":[19,34,115],"its":[20,145],"unique":[21],"dynamics.":[22],"Data-driven":[23],"motion":[25,65],"analysis,":[26],"including":[27],"recognition":[28,66],"and":[29,48,57,98,103,126],"generation,":[30],"often":[32],"limited":[33],"skeletal":[35],"data.":[36],"However,":[37],"data":[38],"other":[40],"modalities,":[41],"such":[42],"as":[43],"audio,":[44],"recorded":[47],"benefit":[49],"downstream":[50],"tasks.":[51],"This":[52],"paper":[53],"explores":[54],"application":[56],"performance":[58],"multimodal":[60,83],"fusion":[61,84,90,95,106,124],"methods":[62,125],"for":[63,82,147],"human":[64],"context":[69],"improvisation.":[72],"We":[73,111,133],"propose":[74],"attention-based":[76],"model,":[77],"component":[78,131],"attention":[79],"network":[80,101],"(CANet),":[81],"on":[85],"three":[86],"levels:":[87],"1)":[88],"feature":[89],"with":[91,96,107],"CANet,":[92],"2)":[93],"model":[94,138],"CANet":[97],"graph":[99],"convolutional":[100],"(GCN),":[102],"3)":[104],"late":[105],"a":[108],"voting":[109],"strategy.":[110],"conduct":[112],"thorough":[113],"experiments":[114],"analyze":[116],"impact":[118],"each":[120],"modality":[121],"different":[123],"distinguish":[127],"critical":[128],"temporal":[129],"or":[130],"features.":[132],"show":[134],"that":[135],"our":[136],"proposed":[137],"outperforms":[139],"two":[141],"baseline":[142],"methods,":[143],"demonstrating":[144],"potential":[146],"analyzing":[148],"dance.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}