{"id":"https://openalex.org/W4387968072","doi":"https://doi.org/10.1145/3581783.3612268","title":"MaTCR: Modality-Aligned Thought Chain Reasoning for Multimodal Task-Oriented Dialogue Generation","display_name":"MaTCR: Modality-Aligned Thought Chain Reasoning for Multimodal Task-Oriented Dialogue Generation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968072","doi":"https://doi.org/10.1145/3581783.3612268"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612268","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612268","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612268","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/10.1145/3581783.3612268","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076444834","display_name":"Yiting Liu","orcid":"https://orcid.org/0000-0001-8736-1498"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiting Liu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420654","display_name":"Liang Li","orcid":"https://orcid.org/0000-0002-1943-8219"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849100","display_name":"Beichen Zhang","orcid":"https://orcid.org/0000-0001-5030-0632"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beichen Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101570133","display_name":"Shan Huang","orcid":"https://orcid.org/0009-0007-9269-3850"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Huang","raw_affiliation_strings":["Tencent Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent Research, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076444834"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.3576,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60518589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5776","last_page":"5785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.995199978351593,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9901999831199646,"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/computer-science","display_name":"Computer science","score":0.8224498629570007},{"id":"https://openalex.org/keywords/semantic-reasoner","display_name":"Semantic reasoner","score":0.6755721569061279},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6213618516921997},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5697824954986572},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5408042669296265},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5136300921440125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48440057039260864},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47848981618881226},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46907681226730347},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43147075176239014},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.42985236644744873},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3996821343898773},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10077041387557983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8224498629570007},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.6755721569061279},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6213618516921997},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5697824954986572},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5408042669296265},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5136300921440125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48440057039260864},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47848981618881226},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46907681226730347},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43147075176239014},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.42985236644744873},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3996821343898773},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10077041387557983},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612268","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612268","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612268","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612268","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612268","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612268","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2446480051","display_name":null,"funder_award_id":"2020108","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3584809445","display_name":null,"funder_award_id":"U19B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4199693610","display_name":null,"funder_award_id":"62236008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4536128632","display_name":null,"funder_award_id":"62322211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G575396328","display_name":null,"funder_award_id":"62225207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6212863906","display_name":null,"funder_award_id":"U21B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6251355785","display_name":null,"funder_award_id":"2020108","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G6258415954","display_name":null,"funder_award_id":"Chinese","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6805594977","display_name":null,"funder_award_id":"202010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7801426869","display_name":null,"funder_award_id":"61931008","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"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968072.pdf","grobid_xml":"https://content.openalex.org/works/W4387968072.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2194775991","https://openalex.org/W2897182555","https://openalex.org/W2956125353","https://openalex.org/W2963748384","https://openalex.org/W2963903950","https://openalex.org/W2981591098","https://openalex.org/W2988023442","https://openalex.org/W3093418251","https://openalex.org/W3096609285","https://openalex.org/W3176763654","https://openalex.org/W3207886649","https://openalex.org/W3214424632","https://openalex.org/W4206621053","https://openalex.org/W4220790454","https://openalex.org/W4226278401","https://openalex.org/W4283688199","https://openalex.org/W4285119160","https://openalex.org/W4296605665","https://openalex.org/W4309938607","https://openalex.org/W4312383651","https://openalex.org/W4384820833","https://openalex.org/W4385573426","https://openalex.org/W4385573814","https://openalex.org/W6803540758"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"In":[0,61],"recent":[1],"years,":[2],"multimodal":[3,29,56,113,120,152,162],"task-oriented":[4,114],"dialogue":[5,30,115],"systems":[6],"have":[7],"attracted":[8],"increasing":[9],"attention":[10],"from":[11,43,128],"communities,":[12],"owing":[13],"to":[14,17,107,136],"their":[15],"ability":[16],"naturally":[18],"and":[19,46,87,131,150,169,201],"efficiently":[20],"provide":[21],"user":[22,126,141],"service.":[23],"Despite":[24],"the":[25,55,64,82,89,138,181,198],"commercial":[26],"value":[27],"of":[28,63,84,91,140,165],"systems,":[31],"they":[32],"are":[33],"still":[34],"confronted":[35],"with":[36,76,176],"two":[37],"challenges:":[38],"(1)":[39],"capture":[40],"users'":[41],"intention":[42],"lengthy":[44],"context":[45],"side":[47],"knowledge":[48],"for":[49,58,69,112,143,154],"question":[50],"comprehension;":[51],"(2)":[52],"jointly":[53],"consider":[54],"information":[57,153],"response":[59],"generation.":[60,116],"view":[62],"challenges,":[65],"previous":[66],"methods":[67,200],"designed":[68],"specific":[70],"scenario":[71],"lack":[72],"auxiliary":[73],"reasoning":[74,110],"structures":[75],"effective":[77],"modality":[78],"interaction,":[79],"which":[80,134],"hinders":[81],"comprehension":[83,139],"user's":[85],"needs":[86],"impedes":[88],"generation":[90],"desired":[92],"responses.":[93,146],"To":[94,147],"address":[95],"these":[96],"issues,":[97],"we":[98,159],"propose":[99],"a":[100,119,161,191],"Modality-aligned":[101],"Thought":[102],"Chain":[103],"Reasoning":[104],"(MaTCR)":[105],"framework":[106],"insert":[108],"explicit":[109],"process":[111],"We":[117,172],"construct":[118],"thought":[121,156],"chain":[122,157],"by":[123],"summarizing":[124],"intermediate":[125],"queries":[127],"aligned":[129],"visual":[130,166],"textual":[132],"context,":[133],"helps":[135],"guide":[137],"intentions":[142],"generating":[144],"reasonable":[145],"effectively":[148],"extract":[149],"integrate":[151],"high-quality":[155],"reasoning,":[158],"design":[160],"reasoner":[163],"consisting":[164],"representation":[167],"learning":[168],"modality-aligned":[170],"fusion.":[171],"comparatively":[173],"justify":[174],"MaTCR":[175,196],"several":[177],"strong":[178],"baselines,":[179],"including":[180],"currently":[182],"highly":[183],"regarded":[184],"large":[185],"language":[186],"model.":[187],"Extensive":[188],"experiments":[189],"over":[190],"benchmark":[192],"dataset":[193],"demonstrate":[194],"that":[195],"outperforms":[197],"existing":[199],"provides":[202],"stronger":[203],"interpretability.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}