{"id":"https://openalex.org/W4408354940","doi":"https://doi.org/10.1109/icassp49660.2025.10890023","title":"Adversarial Training and Cross-modal Feature Fusion in Multimodal Sentiment Analysis","display_name":"Adversarial Training and Cross-modal Feature Fusion in Multimodal Sentiment Analysis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354940","doi":"https://doi.org/10.1109/icassp49660.2025.10890023"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5046113804","display_name":"Junhuai Li","orcid":"https://orcid.org/0000-0001-5483-5175"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Junhuai Li","raw_affiliation_strings":["Xi’an University of Technology,School of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Xi’an University of Technology,School of Computer Science and Engineering,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443730","display_name":"Chuang Lin","orcid":"https://orcid.org/0000-0002-3726-7601"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuang Lin","raw_affiliation_strings":["Xi’an University of Technology,School of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Xi’an University of Technology,School of Computer Science and Engineering,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069263111","display_name":"Huaijun Wang","orcid":"https://orcid.org/0000-0002-2933-6566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaijun Wang","raw_affiliation_strings":["Xi’an University of Technology,School of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Xi’an University of Technology,School of Computer Science and Engineering,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063054691","display_name":"Yuxing Zhi","orcid":"https://orcid.org/0009-0008-9202-4857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxing Zhi","raw_affiliation_strings":["Xi’an University of Technology,School of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Xi’an University of Technology,School of Computer Science and Engineering,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394852","display_name":"Jing Chen","orcid":"https://orcid.org/0000-0002-0024-4561"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Chen","raw_affiliation_strings":["Xi’an University of Technology,School of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Xi’an University of Technology,School of Computer Science and Engineering,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100767738","display_name":"Tao Huang","orcid":"https://orcid.org/0000-0002-8098-8906"},"institutions":[{"id":"https://openalex.org/I86467917","display_name":"James Cook University","ror":"https://ror.org/04gsp2c11","country_code":"AU","type":"education","lineage":["https://openalex.org/I86467917"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tao Huang","raw_affiliation_strings":["James Cook University,Intelligent Computing and Communications (ICC) Lab,Australia"],"affiliations":[{"raw_affiliation_string":"James Cook University,Intelligent Computing and Communications (ICC) Lab,Australia","institution_ids":["https://openalex.org/I86467917"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046113804"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4839,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87810581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8925999999046326,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8925999999046326,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.849399983882904,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.8464999794960022,"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":0.7017795443534851},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6500712633132935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6010574102401733},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.592842698097229},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5251749753952026},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.46325477957725525},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4543636441230774},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4359113872051239},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3911154270172119},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3693748712539673},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34220609068870544},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12190932035446167},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09328258037567139}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7017795443534851},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6500712633132935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6010574102401733},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.592842698097229},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5251749753952026},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.46325477957725525},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4543636441230774},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4359113872051239},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3911154270172119},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3693748712539673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34220609068870544},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12190932035446167},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09328258037567139},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:researchonline.jcu.edu.au:86896","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196352","display_name":"ResearchOnline - JCU (James Cook University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I86467917","host_organization_name":"James Cook University","host_organization_lineage":["https://openalex.org/I86467917"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2556418146","https://openalex.org/W2963063161","https://openalex.org/W2964051877","https://openalex.org/W2964346351","https://openalex.org/W2980520956","https://openalex.org/W3093051361","https://openalex.org/W3098042509","https://openalex.org/W3109389742","https://openalex.org/W3128412859","https://openalex.org/W3206201541","https://openalex.org/W4224933771","https://openalex.org/W4304092664","https://openalex.org/W4366148644","https://openalex.org/W4375868769","https://openalex.org/W4376455521","https://openalex.org/W4387446650","https://openalex.org/W4391582691","https://openalex.org/W4392903371","https://openalex.org/W4401069763","https://openalex.org/W6631190155","https://openalex.org/W6755207826","https://openalex.org/W6797781246"],"related_works":["https://openalex.org/W4205899436","https://openalex.org/W2462138927","https://openalex.org/W3111427900","https://openalex.org/W4302009627","https://openalex.org/W2502115930","https://openalex.org/W4212781403","https://openalex.org/W4388989680","https://openalex.org/W2482350142","https://openalex.org/W2901011898","https://openalex.org/W2619203976"],"abstract_inverted_index":{"Multimodal":[0],"sentiment":[1,143],"analysis":[2],"recognizes":[3],"emotions":[4],"through":[5],"text,":[6],"audio,":[7],"and":[8,27,67,78,93,111,128],"visual":[9],"modalities,":[10,92],"but":[11],"data":[12],"incompleteness":[13],"is":[14,97],"a":[15,44,50,74,79,94,109,123],"major":[16],"challenge.":[17],"Existing":[18],"methods":[19],"often":[20],"focus":[21],"on":[22],"specific":[23],"types":[24,32],"of":[25,33,126,141],"deficiencies":[26],"perform":[28],"poorly":[29],"when":[30],"multiple":[31],"noise":[34],"are":[35,84,105],"present":[36],"simultaneously.":[37],"To":[38],"address":[39],"this":[40,135],"issue,":[41],"we":[42],"propose":[43],"noise-prompted":[45],"adversarial":[46,112],"training":[47,113],"framework":[48],"with":[49,115],"multimodal":[51,142],"interaction":[52],"model":[53,63,121],"to":[54,59,87,99],"enhance":[55],"the":[56,89,100,120,139],"model\u2019s":[57],"robustness":[58],"missing":[60],"modalities.":[61],"The":[62],"first":[64],"extracts":[65],"common":[66],"unique":[68],"features":[69,104],"from":[70],"each":[71],"modality":[72],"using":[73,108],"BERT":[75],"text":[76],"encoder":[77],"shared-private":[80],"encoder.":[81],"Correlation":[82],"measurements":[83],"then":[85],"used":[86],"calculate":[88],"similarity":[90],"between":[91],"weighting":[95],"mechanism":[96],"applied":[98],"shared":[101],"features.":[102],"These":[103],"deeply":[106],"fused":[107],"Transformer,":[110],"combined":[114],"semantic":[116],"reconstruction":[117],"supervision":[118],"helps":[119],"learn":[122],"unified":[124],"representation":[125],"noisy":[127],"clean":[129],"data.":[130],"Experimental":[131],"results":[132],"show":[133],"that":[134],"method":[136],"significantly":[137],"improves":[138],"performance":[140],"analysis.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}