{"id":"https://openalex.org/W4415707909","doi":"https://doi.org/10.1109/icme59968.2025.11209866","title":"Coordinated Uni-modal Assistance for Enhancing Multi-modal Learning","display_name":"Coordinated Uni-modal Assistance for Enhancing Multi-modal Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707909","doi":"https://doi.org/10.1109/icme59968.2025.11209866"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5048174697","display_name":"Hongpeng Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongpeng Pan","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397623","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5245-3584"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2637094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6359999775886536,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6359999775886536,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.06769999861717224,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.046300001442432404,"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/boosting","display_name":"Boosting (machine learning)","score":0.7360000014305115},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6122000217437744},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4397999942302704},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4154999852180481},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.40070000290870667},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38850000500679016},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3334999978542328}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7360000014305115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6370000243186951},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6122000217437744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4887000024318695},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.37229999899864197},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3334999978542328},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C164065428","wikidata":"https://www.wikidata.org/wiki/Q1201929","display_name":"Core competency","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2471695703","https://openalex.org/W2619697695","https://openalex.org/W2760103357","https://openalex.org/W2951937667","https://openalex.org/W2963043696","https://openalex.org/W2965116998","https://openalex.org/W2966765144","https://openalex.org/W3010234023","https://openalex.org/W3035333188","https://openalex.org/W3035570025","https://openalex.org/W3187172219","https://openalex.org/W3206808041","https://openalex.org/W4283796148","https://openalex.org/W4285107355","https://openalex.org/W4304014288","https://openalex.org/W4312639100","https://openalex.org/W4386076642","https://openalex.org/W4390873518","https://openalex.org/W4390873652","https://openalex.org/W4402660166","https://openalex.org/W4402703093","https://openalex.org/W4402979766"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"multi-modal":[1,23,63,92,139],"learning":[2,25,34,80],"methods":[3],"often":[4],"struggle":[5],"with":[6,81],"modality":[7,29],"imbalance":[8],"in":[9,151],"real-world":[10],"applications,":[11],"leading":[12],"to":[13,31,50,100],"suboptimal":[14],"performance.":[15,72,135],"A":[16],"core":[17],"reason":[18],"is":[19,149],"that":[20],"under":[21],"the":[22,27,33,57,102,122,129],"joint":[24],"paradigm,":[26],"dominant":[28],"tends":[30],"control":[32],"process,":[35],"leaving":[36],"non-dominant":[37],"modalities":[38],"insufficiently":[39],"learned":[40],"and":[41,65],"underutilized.":[42],"Some":[43],"attempts":[44],"naturally":[45],"introduce":[46],"additional":[47],"uni-modal":[48,66,89,125],"objectives":[49,64],"alleviate":[51],"this":[52,75],"issue.":[53],"However,":[54],"they":[55],"overlook":[56],"problem":[58],"of":[59,105,124,131],"optimization":[60,112],"conflicts":[61],"between":[62],"objectives,":[67],"which":[68,86],"adversely":[69],"impact":[70],"overall":[71],"To":[73],"address":[74],"challenge,":[76],"we":[77,120],"propose":[78],"Multi-modal":[79],"Coordinative":[82],"Uni-modal":[83],"assisTance":[84],"(MCUT),":[85],"incorporates":[87],"collaborative":[88],"tasks":[90,126],"alongside":[91],"tasks.":[93],"Specifically,":[94],"it":[95],"leverages":[96],"a":[97],"meta-optimization":[98],"approach":[99],"maximize":[101],"inner":[103],"product":[104],"gradients":[106],"originating":[107],"from":[108],"both":[109],"tasks,":[110],"alleviating":[111],"conflicts.":[113],"Moreover,":[114],"based":[115],"on":[116,137],"gradient":[117],"fusion":[118],"analysis,":[119],"enhance":[121],"assistance":[123],"by":[127],"weighting":[128],"phases":[130],"meta-optimization,":[132],"further":[133],"boosting":[134],"Experiments":[136],"multiple":[138],"datasets":[140],"demonstrate":[141],"MCUT\u2019s":[142],"superiority":[143],"over":[144],"existing":[145],"methods.":[146],"The":[147],"code":[148],"available":[150],"https://github.com/njustkmg/ICME25-MCUT.":[152]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-30T00:00:00"}