{"id":"https://openalex.org/W4304080418","doi":"https://doi.org/10.1145/3503161.3547906","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","display_name":"MIntRec: A New Dataset for Multimodal Intent Recognition","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080418","doi":"https://doi.org/10.1145/3503161.3547906"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547906","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547906","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547906","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547906","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020655643","display_name":"Hanlei Zhang","orcid":"https://orcid.org/0000-0003-3448-6793"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanlei Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086201515","display_name":"Hua Xu","orcid":"https://orcid.org/0000-0002-7401-307X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Xu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022927606","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I34155123","display_name":"Hebei University of Science and Technology","ror":"https://ror.org/05h3pkk68","country_code":"CN","type":"education","lineage":["https://openalex.org/I34155123"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Tsinghua University; Hebei University of Science and Technology, Beijing, Shijiazhuang, China","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University; Hebei University of Science and Technology, Beijing, Shijiazhuang, China","institution_ids":["https://openalex.org/I34155123","https://openalex.org/I99065089","https://openalex.org/I92403157"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047886817","display_name":"Qianrui Zhou","orcid":"https://orcid.org/0000-0002-6550-5216"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianrui Zhou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087501435","display_name":"Shaojie Zhao","orcid":"https://orcid.org/0000-0002-5141-9376"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]},{"id":"https://openalex.org/I34155123","display_name":"Hebei University of Science and Technology","ror":"https://ror.org/05h3pkk68","country_code":"CN","type":"education","lineage":["https://openalex.org/I34155123"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojie Zhao","raw_affiliation_strings":["Tsinghua University; Hebei University of Science and Technology, Beijing, China","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University; Hebei University of Science and Technology, Beijing, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I92403157","https://openalex.org/I34155123"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010956440","display_name":"Jiayan Teng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayan Teng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5020655643"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.9894,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96422893,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1688","last_page":"1697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.988099992275238,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9864000082015991,"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/computer-science","display_name":"Computer science","score":0.8400458097457886},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7069380283355713},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.67498779296875},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6549270153045654},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6275429725646973},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5905504822731018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.511006236076355},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4485000967979431},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.43421879410743713},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.4105619490146637},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37832900881767273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37023451924324036},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32602182030677795},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11154145002365112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8400458097457886},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7069380283355713},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.67498779296875},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6549270153045654},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6275429725646973},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5905504822731018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511006236076355},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4485000967979431},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.43421879410743713},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.4105619490146637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37832900881767273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37023451924324036},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32602182030677795},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11154145002365112},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547906","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547906","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547906","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3503161.3547906","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547906","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547906","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4675302116","display_name":null,"funder_award_id":"62173195","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304080418.pdf","grobid_xml":"https://content.openalex.org/works/W4304080418.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1847618513","https://openalex.org/W1861492603","https://openalex.org/W2077302143","https://openalex.org/W2127141656","https://openalex.org/W2166637769","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2251410829","https://openalex.org/W2786860129","https://openalex.org/W2787581402","https://openalex.org/W2883409523","https://openalex.org/W2890399523","https://openalex.org/W2913059114","https://openalex.org/W2937328183","https://openalex.org/W2951937667","https://openalex.org/W2952409498","https://openalex.org/W2963033987","https://openalex.org/W2963150697","https://openalex.org/W2963349408","https://openalex.org/W2963383024","https://openalex.org/W2963686995","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964346351","https://openalex.org/W2965002127","https://openalex.org/W2970217405","https://openalex.org/W2971167298","https://openalex.org/W2971278746","https://openalex.org/W2979826702","https://openalex.org/W2986193249","https://openalex.org/W2998721586","https://openalex.org/W3001071799","https://openalex.org/W3016098309","https://openalex.org/W3034266838","https://openalex.org/W3034849760","https://openalex.org/W3035473672","https://openalex.org/W3045492832","https://openalex.org/W3093051361","https://openalex.org/W3093187109","https://openalex.org/W3104536742","https://openalex.org/W3112240880","https://openalex.org/W3116298410","https://openalex.org/W3173488222","https://openalex.org/W3173528751","https://openalex.org/W3174620475","https://openalex.org/W3174839159","https://openalex.org/W3176023283","https://openalex.org/W3176724088","https://openalex.org/W3206008172","https://openalex.org/W4214701094","https://openalex.org/W4246668299","https://openalex.org/W4301409532"],"related_works":["https://openalex.org/W4205899436","https://openalex.org/W2462138927","https://openalex.org/W3111427900","https://openalex.org/W4302009627","https://openalex.org/W4212781403","https://openalex.org/W4388989680","https://openalex.org/W2373442452","https://openalex.org/W3160379098","https://openalex.org/W3039174484","https://openalex.org/W4287728368"],"abstract_inverted_index":{"Multimodal":[0],"intent":[1,17,47,59,90,128,174],"recognition":[2,18,48],"is":[3,113],"a":[4,42],"significant":[5],"task":[6,191],"for":[7,45,109,115,173,192,202],"understanding":[8],"human":[9],"language":[10],"in":[11,22,100],"real-world":[12],"multimodal":[13,25,46,86,144,171],"scenes.":[14],"Most":[15],"existing":[16],"methods":[19,146,181],"have":[20],"limitations":[21],"leveraging":[23],"the":[24,29,32,63,67,125,155,163,167,179,185,193],"information":[26,172],"due":[27],"to":[28,50,117,123,147],"restrictions":[30],"of":[31,74,98,127,169,189],"benchmark":[33],"datasets":[34],"with":[35,78,162],"only":[36],"text":[37],"information.":[38],"This":[39],"paper":[40],"introduces":[41],"novel":[43],"dataset":[44,72,197],"(MIntRec)":[49],"address":[51],"this":[52,190],"issue.":[53],"It":[54],"formulates":[55],"coarse-grained":[56],"and":[57,81,84,104,136,182,187,198],"fine-grained":[58],"taxonomies":[60],"based":[61],"on":[62],"data":[64],"collected":[65],"from":[66,133],"TV":[68],"series":[69],"Superstore.":[70],"The":[71,176,195],"consists":[73],"2,224":[75],"high-quality":[76],"samples":[77],"text,":[79],"video,":[80],"audio":[82],"modalities":[83,122,157],"has":[85],"annotations":[87],"among":[88],"twenty":[89],"categories.":[91],"Furthermore,":[92],"we":[93],"provide":[94],"annotated":[95],"bounding":[96],"boxes":[97],"speakers":[99],"each":[101,134],"video":[102],"segment":[103],"achieve":[105],"an":[106],"automatic":[107],"process":[108],"speaker":[110],"annotation.":[111],"MIntRec":[112],"helpful":[114],"researchers":[116],"mine":[118],"relationships":[119],"between":[120,178],"different":[121],"enhance":[124],"capability":[126],"recognition.":[129,175],"We":[130],"extract":[131],"features":[132],"modality":[135],"model":[137],"cross-modal":[138],"interactions":[139],"by":[140],"adapting":[141],"three":[142],"powerful":[143],"fusion":[145],"build":[148],"baselines.":[149],"Extensive":[150],"experiments":[151],"show":[152],"that":[153],"employing":[154],"non-verbal":[156],"achieves":[158],"substantial":[159],"improvements":[160],"compared":[161],"text-only":[164],"modality,":[165],"demonstrating":[166],"effectiveness":[168],"using":[170],"gap":[177],"best-performing":[180],"humans":[183],"indicates":[184],"challenge":[186],"importance":[188],"community.":[194],"full":[196],"codes":[199],"are":[200],"available":[201],"use":[203],"at":[204],"https://github.com/thuiar/MIntRec.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}