{"id":"https://openalex.org/W4392909581","doi":"https://doi.org/10.1109/icassp48485.2024.10446825","title":"CLIP-MSA: Incorporating Inter-Modal Dynamics and Common Knowledge to Multimodal Sentiment Analysis With Clip","display_name":"CLIP-MSA: Incorporating Inter-Modal Dynamics and Common Knowledge to Multimodal Sentiment Analysis With Clip","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909581","doi":"https://doi.org/10.1109/icassp48485.2024.10446825"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5029973745","display_name":"Qi Huang","orcid":"https://orcid.org/0000-0003-1073-7471"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Huang","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104260167","display_name":"Pingting Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingting Cai","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042847028","display_name":"Tanyue Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tanyue Nie","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440528","display_name":"Jinshan Zeng","orcid":"https://orcid.org/0000-0003-1719-3358"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinshan Zeng","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I53592917"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8145","last_page":"8149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9836000204086304,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9836000204086304,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9789999723434448,"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/T10028","display_name":"Topic Modeling","score":0.9646000266075134,"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":0.7165586352348328},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6241134405136108},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4987447261810303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46404191851615906},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3524821102619171},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3306533694267273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7165586352348328},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6241134405136108},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4987447261810303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46404191851615906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3524821102619171},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3306533694267273},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2255466643","https://openalex.org/W2341528187","https://openalex.org/W2808359495","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964346351","https://openalex.org/W2996428491","https://openalex.org/W3012721484","https://openalex.org/W3034266838","https://openalex.org/W3036601975","https://openalex.org/W3093051361","https://openalex.org/W3098042509","https://openalex.org/W3101998545","https://openalex.org/W3128412859","https://openalex.org/W3176445421","https://openalex.org/W3197875592","https://openalex.org/W3214432797","https://openalex.org/W4285262944","https://openalex.org/W4385245566","https://openalex.org/W4385573062","https://openalex.org/W6638667902","https://openalex.org/W6752724743","https://openalex.org/W6768021236","https://openalex.org/W6780218876","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W3089396779","https://openalex.org/W2548633793","https://openalex.org/W3013279174","https://openalex.org/W2941935829","https://openalex.org/W2596247554","https://openalex.org/W4301373556","https://openalex.org/W3132372214","https://openalex.org/W4224284088","https://openalex.org/W4286571989","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multimodal":[0],"Sentiment":[1],"Analysis":[2],"(MSA)":[3],"aims":[4],"to":[5],"yield":[6,40],"the":[7,44,51,60,67,83,90,96,103,123],"sentiment":[8],"polarities":[9],"of":[10,31,53,62,92,140],"speakers":[11],"in":[12,33,59,66,138],"video":[13],"streams":[14],"based":[15],"on":[16,130,136],"multiple":[17],"modal":[18,46],"features":[19,47],"such":[20],"as":[21],"textual,":[22,104],"acoustic":[23,105],"and":[24,27,56,86,101,106,132],"visual":[25,107],"features,":[26],"has":[28],"attracted":[29],"amounts":[30],"attention":[32],"recent":[34],"years.":[35],"Existing":[36],"MSA":[37,77],"models":[38,129],"often":[39],"unimodal":[41,63,93],"embeddings":[42],"from":[43],"associated":[45],"individually,":[48],"while":[49],"overlooking":[50],"importance":[52],"inter-modal":[54,84],"dynamics":[55,85],"common":[57,87],"knowledge":[58,88],"extraction":[61],"embeddings,":[64],"resulting":[65],"limited":[68],"performance.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"suggest":[74],"a":[75,110],"novel":[76],"model":[78,125],"called":[79],"CLIP-MSA":[80],"through":[81],"incorporating":[82],"into":[89],"generation":[91],"representations":[94,108],"with":[95,109],"Contrastive":[97],"Language-Image":[98],"Pre-training":[99],"(CLIP),":[100],"fusing":[102],"hierarchical":[111],"co-attention":[112],"mechanism.":[113],"Numerous":[114],"experimental":[115],"results":[116],"over":[117],"two":[118],"benchmark":[119],"datasets":[120],"show":[121],"that":[122],"proposed":[124],"outperforms":[126],"existing":[127],"state-of-the-art":[128],"CMU-MOSI,":[131],"provides":[133],"competitive":[134],"performance":[135],"CMU-MOSEI,":[137],"terms":[139],"four":[141],"commonly":[142],"used":[143],"evaluation":[144],"metrics.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}