{"id":"https://openalex.org/W4415540836","doi":"https://doi.org/10.1145/3746027.3754820","title":"A Theoretical Proof of Dynamic Multimodal Fusion Exacerbates Modality Greedy","display_name":"A Theoretical Proof of Dynamic Multimodal Fusion Exacerbates Modality Greedy","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540836","doi":"https://doi.org/10.1145/3746027.3754820"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754820","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5101347561","display_name":"Xiaorui Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaorui Ding","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102883992","display_name":"Huan Ma","orcid":"https://orcid.org/0009-0000-4448-9897"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Ma","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100604573","display_name":"Changqing Zhang","orcid":"https://orcid.org/0000-0003-1410-6650"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changqing Zhang","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101347561"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16034014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2429","last_page":"2436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.989300012588501,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.989300012588501,"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/T12031","display_name":"Speech and dialogue systems","score":0.961899995803833,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9584000110626221,"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/spurious-relationship","display_name":"Spurious relationship","score":0.6940000057220459},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6822999715805054},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5618000030517578},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5303000211715698},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4244000017642975},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4052000045776367}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6940000057220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692799985408783},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6822999715805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5674999952316284},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5618000030517578},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49720001220703125},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34119999408721924},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C174988536","wikidata":"https://www.wikidata.org/wiki/Q5318965","display_name":"Dynamic decision-making","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754820","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6091885538","display_name":null,"funder_award_id":"62376193, 61925602","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1923184257","https://openalex.org/W1943054406","https://openalex.org/W2964027659","https://openalex.org/W3035333188","https://openalex.org/W3093051361","https://openalex.org/W3174690404","https://openalex.org/W3176404283","https://openalex.org/W3192206917","https://openalex.org/W4224926219","https://openalex.org/W4312639100","https://openalex.org/W4313007055","https://openalex.org/W4313420087","https://openalex.org/W4385801378","https://openalex.org/W4393156830","https://openalex.org/W4401815590"],"related_works":[],"abstract_inverted_index":{"In":[0,94,117],"recent":[1],"years,":[2],"numerous":[3],"studies":[4],"have":[5],"proposed":[6],"uncertainty-guided":[7],"multimodal":[8,19,76,127,145],"learning":[9,128],"to":[10,12,25,71],"adapt":[11],"dynamic":[13,58,104,126,144],"relationships":[14],"between":[15],"different":[16],"modalities.":[17,93],"Dynamic":[18],"fusion":[20,31,59,105],"enables":[21],"more":[22],"dominant":[23],"modalities":[24,43],"receive":[26],"greater":[27],"weight":[28],"during":[29,60],"the":[30,35,55,63,90,122],"process,":[32],"thereby":[33],"preventing":[34],"influence":[36],"of":[37,57,89],"spurious":[38],"features":[39],"from":[40,129],"less":[41],"reliable":[42],"on":[44],"decision-making.":[45],"However,":[46],"there":[47],"is":[48,149],"No":[49],"free":[50],"lunch.":[51],"We":[52],"observe":[53],"that":[54,83,103,113],"introduction":[56],"training":[61],"exacerbates":[62],"model's":[64],"tendency":[65],"toward":[66],"Greedy":[67,123],"(a":[68],"phenomenon":[69],"known":[70],"induce":[72],"decision":[73],"shortcuts":[74],"in":[75,80,125],"learning).":[77],"This":[78],"results":[79,112],"a":[81,99,137],"model":[82],"does":[84],"not":[85],"fully":[86],"take":[87],"advantage":[88],"lower":[91],"quality":[92],"this":[95,115,119],"paper,":[96],"we":[97,109],"provide":[98],"theoretical":[100,131],"analysis":[101],"showing":[102],"intensifies":[106],"Greedy,":[107],"and":[108,132],"present":[110],"experimental":[111,133],"support":[114],"observation.":[116],"summary,":[118],"paper":[120],"explains":[121],"risk":[124],"both":[130],"perspectives,":[134],"serving":[135],"as":[136],"cautionary":[138],"reminder":[139],"for":[140],"researchers":[141],"when":[142],"employing":[143],"learning.":[146],"Our":[147],"code":[148],"available":[150],"at":[151],"https://github.com/d-xr/GreedyDynFusion.":[152]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}