{"id":"https://openalex.org/W4379806230","doi":"https://doi.org/10.1145/3591106.3592219","title":"MMSF: A Multimodal Sentiment-Fused Method to Recognize Video Speaking Style","display_name":"MMSF: A Multimodal Sentiment-Fused Method to Recognize Video Speaking Style","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806230","doi":"https://doi.org/10.1145/3591106.3592219"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592219","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092114885","display_name":"Beibei Zhang","orcid":"https://orcid.org/0000-0003-4931-9867"},"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":true,"raw_author_name":"Beibei Zhang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0003-4931-9867","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001427581","display_name":"Yaqun Fang","orcid":"https://orcid.org/0009-0001-9065-968X"},"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":"Yaqun Fang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":"https://orcid.org/0009-0001-9065-968X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101824411","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0003-2789-0325"},"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":"Fan Yu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0003-2789-0325","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004613974","display_name":"Jia Bei","orcid":"https://orcid.org/0009-0008-3731-7294"},"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":"Jia Bei","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":"https://orcid.org/0009-0008-3731-7294","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084591510","display_name":"Tongwei Ren","orcid":"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, China"],"raw_orcid":"https://orcid.org/0000-0003-3092-424X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092114885"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.2355,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49870794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9879000186920166,"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":0.7796329259872437},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7127846479415894},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6965113878250122},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6956923007965088},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.6261782050132751},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.561722457408905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49958038330078125},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4507635831832886},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43682897090911865},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3522581458091736},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14941826462745667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7796329259872437},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7127846479415894},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6965113878250122},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6956923007965088},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.6261782050132751},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.561722457408905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49958038330078125},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4507635831832886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43682897090911865},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3522581458091736},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14941826462745667},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592219","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2012210378","https://openalex.org/W2064675550","https://openalex.org/W2082303464","https://openalex.org/W2122563357","https://openalex.org/W2191779130","https://openalex.org/W2807126412","https://openalex.org/W2963992782","https://openalex.org/W2964051877","https://openalex.org/W2981851019","https://openalex.org/W2990503944","https://openalex.org/W3093051361","https://openalex.org/W3128412859","https://openalex.org/W3175859344","https://openalex.org/W3206529771","https://openalex.org/W3214432797","https://openalex.org/W4214612132","https://openalex.org/W4312560592","https://openalex.org/W4312772544","https://openalex.org/W4313038481"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2548633793","https://openalex.org/W2028665553","https://openalex.org/W2941935829","https://openalex.org/W2086519370"],"abstract_inverted_index":{"As":[0],"talking":[1],"takes":[2],"a":[3,32,69],"large":[4],"proportion":[5],"of":[6,16,28,84,92,95],"human":[7,17,96],"lives,":[8],"it":[9,134],"is":[10,22,90,121,135],"necessary":[11],"to":[12,45,114,137],"perform":[13],"deeper":[14],"understanding":[15,126],"conversations.":[18],"Speaking":[19],"style":[20],"recognition":[21],"aimed":[23],"at":[24],"recognizing":[25],"the":[26,93,111,129,138],"styles":[27,55,64],"conversations,":[29],"which":[30,49,75,109],"provides":[31],"fine-grained":[33],"description":[34],"about":[35],"talking.":[36],"Current":[37],"works":[38],"focus":[39],"on":[40,123],"adopting":[41],"only":[42],"visual":[43],"clues":[44],"recognize":[46,62,115],"speaking":[47,54,63,116],"styles,":[48],"cannot":[50],"accurately":[51],"distinguish":[52],"different":[53],"when":[56],"they":[57],"are":[58],"visually":[59],"similar.":[60],"To":[61],"more":[65],"effectively,":[66],"we":[67,98],"propose":[68],"novel":[70],"multimodal":[71,104],"sentiment-fused":[72],"method,":[73],"MMSF,":[74],"extracts":[76],"and":[77,81,128],"integrates":[78],"visual,":[79],"audio":[80],"textual":[82],"features":[83],"videos.":[85],"In":[86],"addition,":[87],"as":[88],"sentiment":[89,101],"one":[91],"motivations":[94],"behavior,":[97],"first":[99],"introduce":[100],"into":[102],"our":[103],"method":[105],"with":[106],"cross-attention":[107],"mechanism,":[108],"enhance":[110],"video":[112,125],"feature":[113],"styles.":[117],"The":[118],"proposed":[119],"MMSF":[120],"evaluated":[122],"long-form":[124],"benchmark,":[127],"experiment":[130],"results":[131],"show":[132],"that":[133],"superior":[136],"state-of-the-arts.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}