{"id":"https://openalex.org/W3210580323","doi":"https://doi.org/10.1145/3461615.3485408","title":"Crossmodal Clustered Contrastive Learning: Grounding of Spoken Language to Gesture","display_name":"Crossmodal Clustered Contrastive Learning: Grounding of Spoken Language to Gesture","publication_year":2021,"publication_date":"2021-10-18","ids":{"openalex":"https://openalex.org/W3210580323","doi":"https://doi.org/10.1145/3461615.3485408","mag":"3210580323"},"language":"en","primary_location":{"id":"doi:10.1145/3461615.3485408","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461615.3485408","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461615.3485408","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","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/10.1145/3461615.3485408","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100398178","display_name":"Dong Won Lee","orcid":"https://orcid.org/0000-0002-6336-5512"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Won Lee","raw_affiliation_strings":["Machine Learning Department, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Department, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050602513","display_name":"Chaitanya Ahuja","orcid":"https://orcid.org/0000-0003-4396-2050"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaitanya Ahuja","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081398601","display_name":"Louis\u2010Philippe Morency","orcid":"https://orcid.org/0000-0001-6376-7696"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis-Philippe Morency","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.2227,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79795706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"202","last_page":"210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9973999857902527,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9973999857902527,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crossmodal","display_name":"Crossmodal","score":0.7931385040283203},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7552800178527832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7456453442573547},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.481008380651474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4555642604827881},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.43114325404167175},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.42234641313552856},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41425979137420654},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1897573471069336},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.06868287920951843}],"concepts":[{"id":"https://openalex.org/C60115397","wikidata":"https://www.wikidata.org/wiki/Q5188732","display_name":"Crossmodal","level":4,"score":0.7931385040283203},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7552800178527832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456453442573547},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.481008380651474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4555642604827881},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.43114325404167175},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.42234641313552856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41425979137420654},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1897573471069336},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.06868287920951843},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.0},{"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:10.1145/3461615.3485408","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461615.3485408","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461615.3485408","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3461615.3485408","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461615.3485408","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461615.3485408","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3210580323.pdf","grobid_xml":"https://content.openalex.org/works/W3210580323.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W164929510","https://openalex.org/W283036004","https://openalex.org/W815877816","https://openalex.org/W1208039178","https://openalex.org/W1901129140","https://openalex.org/W2007337857","https://openalex.org/W2024536104","https://openalex.org/W2035046981","https://openalex.org/W2072617587","https://openalex.org/W2131734538","https://openalex.org/W2141855524","https://openalex.org/W2142824220","https://openalex.org/W2151539117","https://openalex.org/W2161676006","https://openalex.org/W2235920218","https://openalex.org/W2296371640","https://openalex.org/W2727071501","https://openalex.org/W2780124704","https://openalex.org/W2802076562","https://openalex.org/W2901872500","https://openalex.org/W2922298118","https://openalex.org/W2962795401","https://openalex.org/W2967443589","https://openalex.org/W2973049979","https://openalex.org/W2981133004","https://openalex.org/W2981802563","https://openalex.org/W2992492498","https://openalex.org/W3035524453","https://openalex.org/W3083173864","https://openalex.org/W3098994456","https://openalex.org/W3099073275","https://openalex.org/W3102619627","https://openalex.org/W3108316907","https://openalex.org/W3115266783","https://openalex.org/W3125775899","https://openalex.org/W3160799772"],"related_works":["https://openalex.org/W4240440807","https://openalex.org/W953566696","https://openalex.org/W2010220987","https://openalex.org/W2010927954","https://openalex.org/W2085535992","https://openalex.org/W4386123105","https://openalex.org/W3117345873","https://openalex.org/W2067981595","https://openalex.org/W2933405975","https://openalex.org/W2053951134"],"abstract_inverted_index":{"Crossmodal":[0,100],"grounding":[1,30,81],"is":[2],"a":[3,35,52,62,70,95,144],"key":[4],"technical":[5],"challenge":[6],"when":[7],"generating":[8],"relevant":[9,130],"and":[10,55,58,86,150],"well-timed":[11],"gestures":[12,131],"from":[13],"spoken":[14,24,84,109],"language.":[15],"Often,":[16],"the":[17,105,116,119,138],"same":[18],"gesture":[19,36,120],"can":[20,125],"accompany":[21],"semantically":[22,44],"different":[23,45],"language":[25,85,110,133],"phrases":[26,46],"which":[27,112],"makes":[28],"crossmodal":[29],"especially":[31],"challenging.":[32],"For":[33],"example,":[34],"(semi-circular":[37],"with":[38,43,115],"both":[39],"hands)":[40],"could":[41],"co-occur":[42],"\u201dentire":[47],"bottom":[48],"row\u201d":[49],"(referring":[50,60],"to":[51,61,73,78,107,164],"physical":[53],"point)":[54],"\u201dmolecules":[56],"expand":[57],"decay\u201d":[59],"scientific":[63],"phenomena).":[64],"In":[65],"this":[66,91],"paper,":[67],"we":[68,93],"introduce":[69],"self-supervised":[71],"approach":[72,142],"learn":[74,108],"representations":[75,111],"better":[76],"suited":[77],"such":[79],"many-to-one":[80],"relationships":[82],"between":[83],"gestures.":[87],"As":[88],"part":[89],"of":[90,140],"approach,":[92],"propose":[94],"new":[96],"contrastive":[97],"loss":[98],"function,":[99],"Cluster":[101],"NCE,":[102],"that":[103],"guides":[104],"model":[106],"are":[113],"consistent":[114],"similarities":[117],"in":[118],"space.":[121],"This":[122],"gesture-aware":[123],"space":[124],"help":[126],"us":[127],"generate":[128],"more":[129],"given":[132],"as":[134],"input.":[135],"We":[136],"demonstrate":[137],"effectiveness":[139],"our":[141],"on":[143],"publicly":[145],"available":[146],"dataset":[147],"through":[148],"quantitative":[149],"qualitative":[151],"evaluations.":[152],"Our":[153],"proposed":[154],"methodology":[155],"significantly":[156],"outperforms":[157],"prior":[158],"approaches":[159],"for":[160],"gestures-language":[161],"grounding.":[162],"Link":[163],"code:":[165],"https://github.com/dondongwon/CC_NCE_GENEA.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
