{"id":"https://openalex.org/W4413472098","doi":"https://doi.org/10.1109/tip.2025.3599673","title":"Enhancing Multimodal Learning via Hierarchical Fusion Architecture Search With Inconsistency Mitigation","display_name":"Enhancing Multimodal Learning via Hierarchical Fusion Architecture Search With Inconsistency Mitigation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413472098","doi":"https://doi.org/10.1109/tip.2025.3599673","pmid":"https://pubmed.ncbi.nlm.nih.gov/40844955"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3599673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3599673","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5072081771","display_name":"Kaifang Long","orcid":"https://orcid.org/0000-0002-9460-0052"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaifang Long","raw_affiliation_strings":["College of Software, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Software, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075634997","display_name":"Guoyang Xie","orcid":"https://orcid.org/0000-0001-8433-8153"},"institutions":[{"id":"https://openalex.org/I4210142539","display_name":"Guangdong Institute of Intelligent Manufacturing","ror":"https://ror.org/049jpjz09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210142539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoyang Xie","raw_affiliation_strings":["Department of Intelligent Manufacturing, CATL, Ningde, China"],"affiliations":[{"raw_affiliation_string":"Department of Intelligent Manufacturing, CATL, Ningde, China","institution_ids":["https://openalex.org/I4210142539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068061222","display_name":"Lianbo Ma","orcid":"https://orcid.org/0000-0002-9969-211X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianbo Ma","raw_affiliation_strings":["College of Software, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Software, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734609","display_name":"Qing Li","orcid":"https://orcid.org/0000-0002-6071-473X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007392914","display_name":"Min Huang","orcid":"https://orcid.org/0000-0003-3793-968X"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Huang","raw_affiliation_strings":["College of Information Science and Engineering, State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","State Key Laboratory of Synthetical Automation for Process Industries, College of Information Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]},{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089781142","display_name":"Jianhui Lv","orcid":"https://orcid.org/0000-0003-0884-6601"},"institutions":[{"id":"https://openalex.org/I85430964","display_name":"Jinzhou Medical University","ror":"https://ror.org/02yd1yr68","country_code":"CN","type":"education","lineage":["https://openalex.org/I85430964"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhui Lv","raw_affiliation_strings":["First Affiliated Hospital, Jinzhou Medical University, Jinzhou, China","First Affiliated Hospital of Jinzhou Medical University, Jinzhou, China"],"affiliations":[{"raw_affiliation_string":"First Affiliated Hospital, Jinzhou Medical University, Jinzhou, China","institution_ids":["https://openalex.org/I85430964"]},{"raw_affiliation_string":"First Affiliated Hospital of Jinzhou Medical University, Jinzhou, China","institution_ids":["https://openalex.org/I85430964"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027687139","display_name":"Zhichao Lu","orcid":"https://orcid.org/0000-0002-4618-3573"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhichao Lu","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5072081771"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":4.7137,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95013502,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"34","issue":null,"first_page":"5458","last_page":"5472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9527999758720398,"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/T12031","display_name":"Speech and dialogue systems","score":0.9527999758720398,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9138000011444092,"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/computer-science","display_name":"Computer science","score":0.6469857692718506},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5870981216430664},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5627437829971313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5601043701171875},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.4517171382904053},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4485071897506714},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3812099099159241},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36528509855270386},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35683703422546387},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17620891332626343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6469857692718506},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5870981216430664},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5627437829971313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5601043701171875},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.4517171382904053},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4485071897506714},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3812099099159241},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36528509855270386},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35683703422546387},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17620891332626343},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3599673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3599673","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:40844955","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40844955","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3603513928","display_name":null,"funder_award_id":"62472079","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4488810808","display_name":null,"funder_award_id":"No.N2417003","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8060955461","display_name":null,"funder_award_id":"N2417003","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W2117079761","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2767249564","https://openalex.org/W2767915528","https://openalex.org/W2791526950","https://openalex.org/W2888471892","https://openalex.org/W2962850006","https://openalex.org/W2963273301","https://openalex.org/W2963369114","https://openalex.org/W2963446712","https://openalex.org/W2963524571","https://openalex.org/W2964081807","https://openalex.org/W2964134613","https://openalex.org/W2965658867","https://openalex.org/W2970476646","https://openalex.org/W2982378897","https://openalex.org/W3000881061","https://openalex.org/W3034593503","https://openalex.org/W3035570025","https://openalex.org/W3092767330","https://openalex.org/W3096415068","https://openalex.org/W3134776119","https://openalex.org/W3152844947","https://openalex.org/W3175546201","https://openalex.org/W3199394329","https://openalex.org/W4213439605","https://openalex.org/W4224926219","https://openalex.org/W4293518081","https://openalex.org/W4296069129","https://openalex.org/W4313639507","https://openalex.org/W4319300887","https://openalex.org/W4321609025","https://openalex.org/W4367047467","https://openalex.org/W4385570100","https://openalex.org/W4385801378","https://openalex.org/W4386047824","https://openalex.org/W4387969709","https://openalex.org/W4391528166","https://openalex.org/W4391912464","https://openalex.org/W4392939995","https://openalex.org/W4393144919","https://openalex.org/W4393160284","https://openalex.org/W4399880844","https://openalex.org/W4400909686","https://openalex.org/W4401024768","https://openalex.org/W4402673954","https://openalex.org/W4402978308","https://openalex.org/W4403780671","https://openalex.org/W4405953164","https://openalex.org/W4406753804","https://openalex.org/W4407361695","https://openalex.org/W4410496178"],"related_works":["https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3214791684","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969"],"abstract_inverted_index":{"The":[0],"design":[1],"of":[2,157,203],"effective":[3],"multimodal":[4,13,31,158],"feature":[5,149],"fusion":[6,35,65,72,201],"strategies":[7],"is":[8,105],"the":[9,54,70,82,86,101,118,129,145,195,199,214],"key":[10],"task":[11],"for":[12,148],"learning,":[14],"which":[15],"often":[16],"requires":[17],"huge":[18],"computational":[19,182],"costs":[20],"with":[21,38,185],"extensive":[22],"expertise.":[23],"In":[24,81,117,177],"this":[25,222],"paper,":[26],"we":[27,122,136,189],"seek":[28],"to":[29,107,143],"enhance":[30],"learning":[32],"via":[33],"hierarchical":[34,71],"architecture":[36],"search":[37,79,84,120,172],"inconsistency":[39,55,102,197,216],"mitigation.":[40],"Different":[41],"from":[42],"previous":[43],"works,":[44],"our":[45],"Hierarchical":[46],"Fusion":[47],"Multimodal":[48],"Neural":[49],"Architecture":[50],"Search":[51],"(HF-MNAS)":[52],"considers":[53],"in":[56,63,96,114,128],"modalities":[57,111],"and":[58,60,77,88,93,112,174,191,208,211],"labels,":[59],"fine-grained":[61,98],"exploitation":[62],"multi-level":[64],"architectures.":[66],"Specifically,":[67],"it":[68],"disentangles":[69],"problem":[73],"into":[74],"two-level":[75],"(macro-":[76],"micro-level)":[78],"spaces.":[80],"macro-level":[83],"space,":[85,121],"high-level":[87],"low-level":[89],"features":[90],"are":[91],"extracted":[92],"then":[94],"connected":[95],"a":[97,155],"way,":[99],"where":[100],"mitigation":[103,217],"module":[104,218],"designed":[106],"minimize":[108],"discrepancies":[109],"between":[110],"labels":[113],"cell":[115],"outputs.":[116],"micro-level":[119],"find":[123],"that":[124,164,194,213],"different":[125,132],"intermediate":[126],"nodes":[127],"cells":[130,147],"exhibit":[131],"importance":[133],"degrees.":[134],"Then,":[135],"propose":[137],"an":[138],"importance-based":[139],"node":[140],"selection":[141],"mechanism":[142],"form":[144],"optimal":[146],"fusion.":[150],"We":[151],"evaluate":[152],"HF-MNAS":[153,165,179],"on":[154],"series":[156],"classification":[159],"tasks.":[160],"Empirical":[161],"evidence":[162],"shows":[163],"achieves":[166],"competitive":[167],"trade-off":[168],"performance":[169,202],"across":[170],"accuracy,":[171],"time,":[173],"inference":[175],"speed.":[176],"particular,":[178],"consumes":[180],"minimal":[181],"cost":[183],"compared":[184],"state-of-the-art":[186],"MNASs.":[187],"Furthermore,":[188],"theoretically":[190],"experimentally":[192],"verify":[193],"modality-label":[196],"deteriorates":[198],"overall":[200],"models":[204],"such":[205],"as":[206],"accuracy":[207],"F1":[209],"score,":[210],"demonstrate":[212],"proposed":[215],"could":[219],"effectively":[220],"mitigate":[221],"phenomenon.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}