{"id":"https://openalex.org/W4415540663","doi":"https://doi.org/10.1145/3746027.3755258","title":"DFCNet: Dual-Factor Compensatory Clustering Network for Modality-Imbalanced Generalized Zero-Shot Learning","display_name":"DFCNet: Dual-Factor Compensatory Clustering Network for Modality-Imbalanced Generalized Zero-Shot Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540663","doi":"https://doi.org/10.1145/3746027.3755258"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755258","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755258","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":"conference-paper","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":null,"display_name":"Xiangyu Shan","orcid":"https://orcid.org/0009-0009-2730-9394"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Shan","raw_affiliation_strings":["College of Information Engineering, Yangzhou University, Yangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-2730-9394","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Yangzhou University, Yangzhou, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028038471","display_name":"Heng Song","orcid":"https://orcid.org/0000-0001-8495-9582"},"institutions":[{"id":"https://openalex.org/I4210141542","display_name":"Yangzhou Vocational University","ror":"https://ror.org/03sxsay12","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210141542"]},{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Song","raw_affiliation_strings":["College of Information Engineering, Yangzhou University, yangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8495-9582","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Yangzhou University, yangzhou, China","institution_ids":["https://openalex.org/I4210141542","https://openalex.org/I78978612"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100751130","display_name":"Junwu Zhu","orcid":"https://orcid.org/0000-0001-5810-613X"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwu Zhu","raw_affiliation_strings":["College of Information Engineering, Yangzhou University, Yangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5810-613X","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Yangzhou University, Yangzhou, China","institution_ids":["https://openalex.org/I78978612"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"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":"3962","last_page":"3971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965000152587891,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965000152587891,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11609","display_name":"Geophysical Methods and Applications","score":0.9519000053405762,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5823000073432922},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5479000210762024},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4878000020980835},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.47290000319480896},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45100000500679016},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43689998984336853},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.38830000162124634},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3635999858379364},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3617999851703644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6144000291824341},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5479000210762024},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4878000020980835},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45100000500679016},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.35600000619888306},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755258","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755258","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W1970176196","https://openalex.org/W2044913453","https://openalex.org/W2096733369","https://openalex.org/W2194775991","https://openalex.org/W2963545832","https://openalex.org/W2991813857","https://openalex.org/W2997573100","https://openalex.org/W3015371781","https://openalex.org/W4312639100","https://openalex.org/W4312653797","https://openalex.org/W4386076642","https://openalex.org/W4386453567","https://openalex.org/W4387831678","https://openalex.org/W4387968071","https://openalex.org/W4392970297","https://openalex.org/W4398757574","https://openalex.org/W4404038917","https://openalex.org/W4406860152","https://openalex.org/W4407632488","https://openalex.org/W4413679863"],"related_works":[],"abstract_inverted_index":{"In":[0],"audio-visual":[1],"joint":[2],"analysis,":[3],"generalized":[4],"zero-shot":[5],"learning":[6],"(GZSL)":[7],"aims":[8],"to":[9,76,114,147],"recognize":[10],"unseen":[11],"categories":[12],"by":[13],"aligning":[14],"semantic":[15,26,39,92],"information":[16,75],"across":[17,183],"modalities.":[18,32],"However,":[19],"significant":[20],"challenges":[21],"arise":[22],"from":[23],"temporal":[24,104],"and":[25,30,49,69,94,141,199],"discrepancies":[27],"between":[28],"audio":[29],"video":[31],"Traditional":[33],"methods":[34],"typically":[35],"depend":[36],"on":[37],"static":[38],"embeddings,":[40],"thereby":[41],"overlooking":[42],"the":[43,57,119,130,174,177,191,201],"dynamic":[44,67],"nature":[45],"of":[46,72,176,194,203],"these":[47,78],"modalities":[48],"often":[50],"resulting":[51],"in":[52,196,205],"modality":[53,144,207],"imbalance.":[54],"We":[55],"propose":[56],"Dual-Factor":[58,131],"Compensatory":[59,107],"Clustering":[60,132],"Network":[61],"(DFCNet),":[62],"an":[63],"end-to-end":[64],"framework":[65,171],"for":[66,91,102],"fusion":[68],"optimized":[70],"alignment":[71,198],"heterogeneous":[73],"modal":[74],"address":[77],"limitations.":[79],"DFCNet":[80,157],"employs":[81,111],"a":[82,86,95,154],"multi-branch":[83],"architecture,":[84],"integrating":[85],"parallel":[87],"multi-layer":[88],"perceptron":[89],"(MLP)":[90],"modeling":[93],"Bidirectional":[96],"Long":[97],"Short-Term":[98],"Memory":[99],"(BiLSTM)":[100],"network":[101],"capturing":[103],"consistency.":[105],"The":[106,209],"Fusion":[108],"Block":[109],"(CFB)":[110],"tensor":[112],"decomposition":[113,122],"facilitate":[115],"cross-modal":[116,150,197],"coupling,":[117],"where":[118],"low-rank":[120],"representation":[121],"aligns":[123],"intra-modal":[124],"feature":[125],"distributions.":[126],"Additionally,":[127],"we":[128],"introduce":[129],"Multi-objective":[133],"Optimization":[134],"Framework":[135],"(DCMOF),":[136],"which":[137],"ensures":[138],"gradient":[139],"equilibrium":[140],"adaptively":[142],"adjusts":[143],"contribution":[145],"weights":[146],"strengthen":[148],"robust":[149],"alignment.":[151],"Designed":[152],"as":[153],"pluggable":[155],"module,":[156],"can":[158],"be":[159],"seamlessly":[160],"integrated":[161],"into":[162],"existing":[163],"base":[164],"models.":[165],"Experimental":[166],"results":[167],"demonstrate":[168],"that":[169],"our":[170],"significantly":[172],"improves":[173],"performance":[175],"Audio-Visual":[178],"Cross-Modal":[179],"Alignment":[180],"(AVCA)":[181],"model":[182],"multiple":[184],"GZSL":[185],"datasets.":[186],"Ablation":[187],"studies":[188],"further":[189],"validate":[190],"critical":[192],"role":[193],"CFB":[195],"highlight":[200],"significance":[202],"DCMOF":[204],"optimizing":[206],"coordination.":[208],"code":[210],"is":[211],"available":[212],"at":[213],"https://github.com/ATKEROM/DFCNet.":[214]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-25T00:00:00"}