{"id":"https://openalex.org/W7166861419","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1466","title":"Coarse-to-Fine Multimodal Information Selection for Video Speaking Style Recognition with Large Language Models","display_name":"Coarse-to-Fine Multimodal Information Selection for Video Speaking Style Recognition with Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166861419","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1466"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1466","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1466","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1466","pdf_url":"https://aclanthology.org/2026.findings-acl.1466.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.1466.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100441018","display_name":"Beibei Zhang","orcid":"https://orcid.org/0009-0005-2301-8160","observed_orcids":["https://orcid.org/0009-0005-2301-8160"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beibei Zhang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139832895","display_name":"Yanan Lu","orcid":null,"observed_orcids":[]},"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":"Yanan Lu","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139791160","display_name":"Lin Fen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Fen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084591510","display_name":"Tongwei Ren","orcid":"https://orcid.org/0000-0003-3092-424X","observed_orcids":["https://orcid.org/0000-0003-3092-424X"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongwei Ren","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4877809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"29322","last_page":"29337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8589000105857849,"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":0.8589000105857849,"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/T12031","display_name":"Speech and dialogue systems","score":0.10890000313520432,"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/T10383","display_name":"Language, Discourse, Communication Strategies","score":0.005799999926239252,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8840000033378601},{"id":"https://openalex.org/keywords/modality-selection","display_name":"modality selection","score":0.6700000166893005},{"id":"https://openalex.org/keywords/redundant-information","display_name":"information redundancy","score":0.6029999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6740999817848206},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5069000124931335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4885999858379364},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C21338462","wikidata":"https://www.wikidata.org/wiki/Q1662581","display_name":"Information model","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1466","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1466","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1466","pdf_url":"https://aclanthology.org/2026.findings-acl.1466.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1466","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1466","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1466","pdf_url":"https://aclanthology.org/2026.findings-acl.1466.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.6297576427459717,"display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G6452132299","display_name":null,"funder_award_id":"92582103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7458595415","display_name":"\u9762\u5411\u590d\u6742\u573a\u666f\u89c6\u9891\u7684\u89c6\u89c9\u5173\u7cfb\u68c0\u6d4b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072232","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7957610226","display_name":null,"funder_award_id":"JYB2025XDXM118","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/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166861419.pdf","grobid_xml":"https://content.openalex.org/works/W7166861419.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4409363081","https://openalex.org/W4379806230","https://openalex.org/W4408354236","https://openalex.org/W4412887726","https://openalex.org/W4386908242","https://openalex.org/W4416159210","https://openalex.org/W4389519587","https://openalex.org/W7134818525","https://openalex.org/W7166865813","https://openalex.org/W7101986721"],"abstract_inverted_index":{"Video":[0],"Speaking":[1],"Style":[2],"Recognition":[3],"(VSSR)":[4],"aims":[5],"to":[6,137,145],"classify":[7],"conversation":[8],"videos":[9],"into":[10],"different":[11],"types,":[12],"significantly":[13],"facilitating":[14],"human":[15],"interaction":[16],"understanding.Recent":[17],"approaches":[18,170],"explore":[19],"the":[20,42,91,120,140],"potential":[21],"of":[22,93],"large":[23],"language":[24],"models":[25],"(LLM)":[26],"in":[27,45,119],"VSSR":[28,76],"with":[29],"a":[30,72,100,123],"training-free":[31],"process.However,":[32],"directly":[33],"integrating":[34],"all":[35,167],"multimodal":[36,52,81],"data":[37,47,82],"yields":[38],"suboptimal":[39],"results,":[40],"since":[41],"great":[43],"redundancy":[44],"visual":[46,61,124,131],"can":[48],"overshadow":[49],"other":[50],"valuable":[51,56,80],"information,":[53],"such":[54],"as":[55],"textual":[57],"dialogues":[58],"and":[59,113,171],"critical":[60,130],"clues.To":[62],"address":[63],"this,":[64],"we":[65],"propose":[66],"CFMiS":[67,94,160],"(Coarseto-Fine":[68],"Multimodal":[69],"Information":[70],"Selection),":[71],"novel":[73],"framework":[74],"for":[75,89,164],"that":[77,159],"dynamically":[78],"obtain":[79],"via":[83],"coarseto-fine":[84],"selection,":[85],"enhancing":[86],"LLM":[87],"reasoning":[88],"VSSR.Specifically,":[90],"core":[92],"are":[95],"two":[96],"cascaded":[97],"modules:":[98],"1)":[99],"text-dominant":[101],"modality":[102,136],"selection":[103],"module":[104,126],"firstly":[105],"selects":[106],"VSSRrequired":[107],"modalities":[108],"originating":[109],"from":[110,147],"text-based":[111],"prediction;":[112],"2)":[114],"if":[115],"vision":[116],"is":[117,161],"included":[118],"selected":[121,148],"modalities,":[122,149],"refinement":[125],"iteratively":[127],"collects":[128],"VSSR-relevant":[129],"clues.The":[132],"former":[133],"resolves":[134],"which":[135,143],"utilize,":[138],"while":[139],"latter":[141],"determines":[142],"information":[144,152],"adopt":[146],"efficiently":[150],"alleviating":[151],"redundancy.Extensive":[153],"experiments":[154],"on":[155],"multiple":[156],"datasets":[157],"prove":[158],"highly":[162],"effective":[163],"VSSR,":[165],"outperforming":[166],"existing":[168],"trainingfree":[169],"most":[172],"training-based":[173],"methods.":[174]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}