{"id":"https://openalex.org/W7154513978","doi":"https://doi.org/10.48550/arxiv.2604.12518","title":"Enhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis","display_name":"Enhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7154513978","doi":"https://doi.org/10.48550/arxiv.2604.12518"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.12518","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12518","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.12518","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129726986","display_name":"Kang He","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"He, Kang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133658220","display_name":"Yuzhe Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Yuzhe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133675341","display_name":"Xinrong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xinrong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133653551","display_name":"Fei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Fei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133658051","display_name":"Chong Teng","orcid":"https://orcid.org/0009-0000-5246-3099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teng, Chong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133691076","display_name":"Donghong Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Donghong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129726986"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.699400007724762,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.699400007724762,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.24009999632835388,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.011500000022351742,"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/leverage","display_name":"Leverage (statistics)","score":0.7182000279426575},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6927000284194946},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6223000288009644},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6198999881744385},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4936999976634979},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4465000033378601},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.36730000376701355},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.34439998865127563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7447999715805054},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7182000279426575},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6927000284194946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6603999733924866},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6223000288009644},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6198999881744385},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4936999976634979},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4255000054836273},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3560999929904938},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.2630999982357025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.12518","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12518","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.12518","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12518","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"sentiment":[1],"analysis":[2],"(MSA)":[3],"integrates":[4],"heterogeneous":[5],"text,":[6],"audio,":[7],"and":[8,41,50,77,129],"visual":[9],"signals":[10],"to":[11,24,34,112],"infer":[12],"human":[13],"emotions.":[14],"While":[15],"recent":[16],"approaches":[17],"leverage":[18],"cross-modal":[19,78],"complementarity,":[20],"they":[21],"often":[22],"struggle":[23],"fully":[25],"utilize":[26],"weaker":[27,81],"modalities.":[28,56,82],"In":[29],"practice,":[30],"dominant":[31,85],"modalities":[32,86],"tend":[33],"overshadow":[35],"non-verbal":[36],"ones,":[37],"inducing":[38],"modality":[39],"competition":[40],"limiting":[42],"overall":[43],"contributions.":[44],"This":[45],"imbalance":[46],"degrades":[47],"fusion":[48,115],"performance":[49,132],"robustness":[51],"under":[52,133],"noisy":[53],"or":[54,126],"missing":[55],"To":[57,83],"address":[58],"this,":[59],"we":[60],"propose":[61],"a":[62,100],"novel":[63],"model,":[64],"Enhance-then-Balance":[65],"Modality":[66,92,106],"Collaboration":[67],"framework":[68],"(EBMC).":[69],"EBMC":[70,123],"improves":[71],"representation":[72],"quality":[73],"via":[74,99],"semantic":[75],"disentanglement":[76],"enhancement,":[79],"strengthening":[80],"prevent":[84],"from":[87],"overwhelming":[88],"others,":[89],"an":[90],"Energy-guided":[91],"Coordination":[93],"mechanism":[94],"achieves":[95,124],"implicit":[96],"gradient":[97],"rebalancing":[98],"differentiable":[101],"equilibrium":[102],"objective.":[103],"Furthermore,":[104],"Instance-aware":[105],"Trust":[107],"Distillation":[108],"estimates":[109],"sample-level":[110],"reliability":[111],"adaptively":[113],"modulate":[114],"weights,":[116],"ensuring":[117],"robustness.":[118],"Extensive":[119],"experiments":[120],"demonstrate":[121],"that":[122],"state-of-the-art":[125],"competitive":[127],"results":[128],"maintains":[130],"strong":[131],"missing-modality":[134],"settings.":[135]},"counts_by_year":[],"updated_date":"2026-04-16T06:09:31.884825","created_date":"2026-04-16T00:00:00"}